© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

GEMMA-3-1B · 7-GEMMASCOPE-2-RES-16K · 13885 ｜ Neuronpedia

Home
Gemma-3-1B
7-GEMMASCOPE-2-RES-16K
13885

INDEX

Explanations

inflexion points

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

下拉

1.48

<0xCE>

1.46

ا

1.40

æs

1.38

ců

1.37

tey

1.34

ICY

1.33

avax

1.32

 корне

1.31

apabb

1.30

POSITIVE LOGITS

γά

1.39

Individual

1.36

_{

1.35

 спор

1.34

individual

1.33

ôm

1.33

 trapped

1.28

 superior

1.27

inform

1.27

 inform

1.27

Activations Density 0.004%

No Known Activations