© 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-3-4B-IT · 17-GEMMASCOPE-2-RES-16K · 8784 ｜ Neuronpedia

Home
Gemma-3-4B-IT
17-GEMMASCOPE-2-RES-16K
8784

INDEX

Explanations

fractions and parts

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 incluso

0.90

াণী

0.83

𝚕

0.81

ুম

0.81

estab

0.80

𝙫

0.80

 нее

0.79

𝚌

0.79

 συμ

0.78

𝖾

0.78

POSITIVE LOGITS

 Fractional

0.89

Ṭ

0.82

 Partial

0.82

quartered

0.81

Quarter

0.81

 Critique

0.80

 Half

0.80

 Minority

0.80

quarter

0.80

 Stairs

0.77

Activations Density 0.157%

No Known Activations