© 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-3-270M · 15-GEMMASCOPE-2-RES-16K · 4280 ｜ Neuronpedia

Home
Gemma-3-270M
15-GEMMASCOPE-2-RES-16K
4280

INDEX

Explanations

budget and price

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-270m-pt/resid_post/layer_15_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

 cias

1.77

—

1.77

吆

1.71

 yako

1.69

](../

1.65

ogn

1.64

你自己

1.61

 grin

1.61

pled

1.60

/>}

1.56

POSITIVE LOGITS

 Trabalho

1.26

 work

1.25

LDS

1.12

 lavoro

1.12

職

1.08

daughter

1.05

 اثر

1.03

 werk

1.02

work

0.99

 Work

0.99

Activations Density 0.143%

No Known Activations