© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

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

GEMMA-3-12B-IT · 12-GEMMASCOPE-2-RES-16K · 3562 ｜ Neuronpedia

Home
Gemma-3-12B-IT
12-GEMMASCOPE-2-RES-16K
3562

INDEX

Explanations

service

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-12b-it/resid_post/layer_12_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

ﺕ

2.08

nél

1.88

्य

1.84

ulasi

1.78

 générale

1.77

isées

1.76

nasium

1.76

 spécifique

1.73

ﺭ

1.73

 externes

1.70

POSITIVE LOGITS

 ಸಲ್ಲ

2.25

с

2.00

1.97

1.95

1.88

1.82

 Serv

1.79

 SERVICE

1.77

س

1.77

1.75

Activations Density 0.122%

No Known Activations