© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

GEMMA-3-1B · 13-GEMMASCOPE-2-RES-16K · 6332 ｜ Neuronpedia

Home
Gemma-3-1B
13-GEMMASCOPE-2-RES-16K
6332

INDEX

Explanations

for help or support

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

 '-')

1.16

rö

1.04

﹃

1.03

NotEmpty

1.02

λογή

1.01

!)

1.01

 colore

1.00

 குரு

0.99

{})

0.98

Dtls

0.98

POSITIVE LOGITS

これらの

1.14

 absolutely

0.99

 undertaking

0.98

 これらの

0.96

 وذلك

0.94

方が

0.93

などが

0.92

のでしょうか

0.90

たちが

0.90

来进行

0.89

Activations Density 1.107%

No Known Activations