© 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-3-270M · 12-GEMMASCOPE-2-RES-16K · 6100 ｜ Neuronpedia

Home
Gemma-3-270M
12-GEMMASCOPE-2-RES-16K
6100

INDEX

Explanations

subtle differences

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_12_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

어야

2.15

PLIC

2.11

ฒ

2.10

zah

2.09

 évalu

2.05

전히

1.85

 thiệu

1.84

 dữ

1.83

ferencia

1.82

 autorisé

1.82

POSITIVE LOGITS

 when

2.12

 sejak

2.08

 everytime

2.07

 whenever

2.00

when

1.93

 perchè

1.92

 since

1.89

 وقتی

1.88

since

1.87

 moods

1.86

Activations Density 0.070%

No Known Activations