© 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-3-1B-IT · 13-GEMMASCOPE-2-RES-16K · 15225 ｜ Neuronpedia

Home
Gemma-3-1B-IT
13-GEMMASCOPE-2-RES-16K
15225

INDEX

Explanations

less than or equal

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-1b-it/resid_post/layer_13_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

 year

0.82

事

0.80

 week

0.79

Year

0.75

now

0.73

 Year

0.73

Chapter

0.71

Week

0.71

 Paper

0.70

 paper

0.70

POSITIVE LOGITS

াগর

0.98

 navigateur

0.98

嚮

0.96

流域

0.96

醀

0.96

餑

0.95

 paysans

0.94

<unused306>

0.94

<unused1810>

0.94

 Helvetica

0.93

Activations Density 0.019%

No Known Activations