© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116719
    Prev
    Next
    INDEX
    Explanations

    FW, RE, subject, Forward

    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
    Not in Any Lists

    No Comments

    Negative Logits
    /<
    -0.06
    /
    -0.06
    Data
    -0.06
     até
    -0.06
    차가
    -0.06
    data
    -0.05
    :<
    -0.05
    ‌
    -0.05
     φι
    -0.05
     data
    -0.05
    POSITIVE LOGITS
     पहिले
    0.07
    とても
    0.07
     پہلی
    0.07
     maintains
    0.06
    したら
    0.06
     Industrie
    0.06
     repeats
    0.06
     labai
    0.06
     mantiene
    0.06
     notifies
    0.06
    Activations Density 0.001%

    No Known Activations