© 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 · 102589 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
102589

INDEX

Explanations

square

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

square meter

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

ك

0.72

ק

0.60

وبة

0.57

ف

0.56

krb

0.52

၉

0.52

ة

0.50

קד

0.50

dst

0.49

شده

0.49

POSITIVE LOGITS

 square

0.95

 квадрат

0.89

Square

0.83

 Square

0.82

 Squares

0.82

 quadrado

0.81

 squaring

0.80

 cuadrado

0.79

 quadrados

0.79

 제곱

0.78

Activations Density 0.180%

No Known Activations