© 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 · 17-GEMMASCOPE-2-RES-16K · 488 ｜ Neuronpedia

Home
Gemma-3-1B
17-GEMMASCOPE-2-RES-16K
488

INDEX

Explanations

negation and contradictions

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_17_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

*=

1.01

 voidaan

1.00

是以

0.96

*,

0.96

Horizontal

0.95

 ezingu

0.95

 আছে

0.95

-,

0.94

(),

0.92

 অর্থাৎ

0.92

POSITIVE LOGITS

1.31

not

1.20

NOT

1.10

’

1.10

 না

1.06

'...

1.05

not

1.00

ʻ

0.98

actment

0.98

 не

0.98

Activations Density 0.552%

No Known Activations