© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

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

GEMMA-3-1B · 7-GEMMASCOPE-2-RES-16K · 14557 ｜ Neuronpedia

Home
Gemma-3-1B
7-GEMMASCOPE-2-RES-16K
14557

INDEX

Explanations

peer influence and pressure

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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

ﻌ

2.42

legged

2.27

Მ

2.27

ू

2.24

丅

2.24

䅞

2.11

酘

2.09

 Scripture

2.05

ewarm

2.05

 Scriptures

2.02

POSITIVE LOGITS

<bos>

2.15

如同

1.61

 очеред

1.59

焉

1.58

конец

1.55

nb

1.55

Ai

1.54

フィス

1.50

 lark

1.49

 والله

1.48

Activations Density 0.001%

No Known Activations