© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-3-27B · 31-GEMMASCOPE-2-RES-262K · 227098 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
227098

INDEX

Explanations

links and URLs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

羧

0.50

lastCursor

0.50

pathTo

0.47

 nguyên

0.46

 स्तंभ

0.46

 vòng

0.46

{(-

0.46

 phthal

0.46

 στό

0.45

 tốc

0.45

POSITIVE LOGITS

0.58

דע

0.53

 Leute

0.46

0.46

 informieren

0.45

MOS

0.44

OC

0.44

 vivir

0.44

 connu

0.44

“

0.43

Activations Density 0.001%

No Known Activations