© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GEMMA-3-27B · 31-GEMMASCOPE-2-RES-262K · 225316 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
225316

INDEX

Explanations

favourable audit

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

Negative Logits

 isometry

0.50

iotensin

0.43

 läh

0.43

ל

0.43

 influence

0.43

 linie

0.43

ège

0.42

สาย

0.42

0.42

 aikana

0.41

POSITIVE LOGITS

QUIT

0.49

}-

0.48

quit

0.47

routed

0.46

 housed

0.45

 relinquished

0.45

 QUIT

0.45

Routed

0.44

conex

0.44

 cuchar

0.44

Activations Density 0.001%

No Known Activations