---
title: "Peking University Finds a Hidden Reasoning Gauge Inside Every LLM"
subtitle: "A new paper shows the L2 norm of a model's hidden states is a built-in meter for reasoning intensity, enabling three training-free techniques that boost performance on AIME, GPQA, and GSM8K."
url: "https://alphasignal.ai/news/peking-university-finds-a-hidden-reasoning-gauge-inside-every-llm"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-06-04T00:00:00.000Z"
updated: "2026-06-15T00:44:34.864Z"
type: "Paper"
topics:
  - "Reasoning"
  - "Llms"
subtopics:
  - "Math Reasoning"
  - "Long Context"
upvotes: 1574
source_url: "https://arxiv.org/abs/2606.06188"
comments: 0
truncated: true
---

# Peking University Finds a Hidden Reasoning Gauge Inside Every LLM

> A new paper shows the L2 norm of a model's hidden states is a built-in meter for reasoning intensity, enabling three training-free techniques that boost performance on AIME, GPQA, and GSM8K.

What if your LLM already carries a built-in gauge for how hard it is thinking, and you just never looked at it? That is the core claim of a new paper from researchers at Peking University: the **L2 norm** (the Euclidean length of a vector) of a transformer's hidden states is a reliable, model-intrinsic signal of reasoning intensity, layer by layer. And once you can read that signal, you can use it to make the model reason better, without any fine-tuning or extra data.

_Preview only. Full text requires an AlphaSignal Pro account._
