© 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 · 7-GEMMASCOPE-2-RES-16K · 11203 ｜ Neuronpedia

Home
Gemma-3-1B
7-GEMMASCOPE-2-RES-16K
11203

INDEX

Explanations

C++ cin input

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

ت

3.04

𝒐

2.95

𝒆

2.92

𝒂

2.78

ا

2.64

০

2.56

ా

2.54

고

2.47

𝒖

2.37

ي

2.36

POSITIVE LOGITS

обходимо

2.24

dataProvider

2.17

 isActive

2.17

कारात्मक

2.12

üss

2.11

 bounds

2.07

लब्

2.07

Jlc

2.06

ielleicht

2.04

theless

2.01

Activations Density 0.000%

No Known Activations