© 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. 117211
    Prev
    Next
    INDEX
    Explanations

    apache license links

    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
     根据
    -0.07
     quizá
    -0.06
     Perhaps
    -0.06
     শিশুকে
    -0.06
     std
    -0.06
     perhaps
    -0.06
    <0xE3>
    -0.06
    ProjectReference
    -0.06
     lorsqu
    -0.06
     situazione
    -0.06
    POSITIVE LOGITS
     хочет
    0.06
     these
    0.06
     هذه
    0.06
    bleshooting
    0.05
     begyn
    0.05
    expect
    0.05
     этом
    0.05
    Ç
    0.05
    digital
    0.05
     Scoring
    0.05
    Activations Density 0.007%

    No Known Activations