© 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. 116943
    Prev
    Next
    INDEX
    Explanations

    account, series, values, camera, buffer

    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
     rodzaj
    -0.06
    今回
    -0.06
     tercero
    -0.06
     Permit
    -0.06
     salida
    -0.06
     centrales
    -0.06
     يوجد
    -0.06
    образной
    -0.06
    求解
    -0.06
     مدل
    -0.06
    POSITIVE LOGITS
     वास्तव
    0.06
     चयन
    0.06
    非常
    0.06
     suggesting
    0.06
    popUp
    0.06
     अंडरस्टैंड
    0.06
    恹
    0.06
     которые
    0.05
    ature
    0.05
     contribute
    0.05
    Activations Density 0.003%

    No Known Activations