© 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 · 13-GEMMASCOPE-2-RES-16K · 2448 ｜ Neuronpedia

Home
Gemma-3-1B
13-GEMMASCOPE-2-RES-16K
2448

INDEX

Explanations

Examples for writing

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

屶

1.44

isatie

1.44

लॉक

1.39

夻

1.35

㳯

1.35

ueel

1.33

扌

1.33

菂

1.32

 permanente

1.31

iselt

1.28

POSITIVE LOGITS

ч

1.14

1.14

poetry

1.06

ZUKI

1.03

ద

1.02

 Verse

1.01

 Tacoma

1.01

 rejo

0.99

 Bloss

0.98

ero

0.98

Activations Density 0.000%

No Known Activations