© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115876
    Prev
    Next
    INDEX
    Explanations

    news broadcasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    本地
    -0.08
     местные
    -0.07
     local
    -0.07
    เพราะ
    -0.07
    城市
    -0.07
     мест
    -0.06
     مقامی
    -0.06
     பெரிய
    -0.06
     местных
    -0.06
     स्थानीय
    -0.06
    POSITIVE LOGITS
    ensions
    0.06
     Reviewed
    0.06
    Suzanne
    0.06
    实话
    0.06
     pods
    0.06
     সংখ্যক
    0.06
    量を
    0.06
     reviewed
    0.06
     outreach
    0.06
    pods
    0.06
    Activations Density 0.004%

    No Known Activations