© 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 · 13-GEMMASCOPE-2-RES-16K · 13599 ｜ Neuronpedia

Home
Gemma-3-1B
13-GEMMASCOPE-2-RES-16K
13599

INDEX

Explanations

harm violence corruption danger

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_13_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

ar

1.20

stev

1.10

dub

1.07

Suz

1.06

𝑎

1.05

vier

1.04

carbox

1.04

disamb

1.03

roll

1.02

kub

1.01

POSITIVE LOGITS

ถ้า

1.50

 Если

1.39

如果

1.36

 ถ้า

1.36

 DialogInterface

1.29

要是

1.28

我们

1.28

如果我们

1.28

 Độ

1.26

 เรา

1.25

Activations Density 0.000%

No Known Activations