© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

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

GEMMA-3-4B-IT · 22-GEMMASCOPE-2-RES-16K · 10027 ｜ Neuronpedia

Home
Gemma-3-4B-IT
22-GEMMASCOPE-2-RES-16K
10027

INDEX

Explanations

technical content

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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

Jaw

0.95

اً

0.93

jie

0.92

jk

0.88

 mettre

0.86

atherine

0.86

indre

0.84

jev

0.84

nje

0.83

 وقال

0.81

POSITIVE LOGITS

 Pran

1.18

 incumbent

1.08

PRESS

1.06

秞

1.06

𝘮

1.05

 Paints

1.05

𝙢

1.04

设计

1.01

戤

1.00

𝙎

1.00

Activations Density 0.000%

No Known Activations