© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-3-27B-IT · 31-GEMMASCOPE-2-RES-65K · 7276 ｜ Neuronpedia

Home
Gemma-3-27B-IT
31-GEMMASCOPE-2-RES-65K
7276

INDEX

Explanations

code punctuation and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hesap

0.36

oretically

0.36

韫

0.36

WallArray

0.35

 logique

0.35

Listo

0.34

 écoul

0.34

蓣

0.33

verständlich

0.33

媺

0.33

POSITIVE LOGITS

based

0.39

gras

0.36

PA

0.35

CHD

0.34

Canada

0.34

 université

0.34

GOLD

0.34

core

0.33

JA

0.33

east

0.33

Activations Density 0.139%

No Known Activations