© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-3-12B-IT · 12-GEMMASCOPE-2-RES-262K · 6 ｜ Neuronpedia

Home
Gemma-3-12B-IT
12-GEMMASCOPE-2-RES-262K
6

INDEX

Explanations

sneak or creep

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_262k_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

ਨ

1.74

ک

1.72

 koń

1.62

 favorably

1.62

서

1.61

ュー

1.59

Platforms

1.59

 capitalized

1.55

ların

1.53

 încep

1.52

POSITIVE LOGITS

ان

2.16

و

2.03

1.98

1.91

1.88

1.88

LAND

1.86

1.82

اب

1.80

en

1.77

Activations Density 0.057%

No Known Activations