© 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. 120122
    Prev
    Next
    INDEX
    Explanations

    software licenses

    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
    Another
    -0.06
    剧情
    -0.06
     nieruchomości
    -0.06
    oplastic
    -0.06
     Ciência
    -0.06
    ビス
    -0.06
     anticon
    -0.06
    皖
    -0.06
    另外
    -0.06
     another
    -0.06
    POSITIVE LOGITS
     jednotliv
    0.07
     melibatkan
    0.06
     καλύτε
    0.06
    ㄦ
    0.06
     тако
    0.06
     퇴
    0.06
    เหล่า
    0.06
     самой
    0.06
     permasalahan
    0.06
     ตำ
    0.06
    Activations Density 0.009%

    No Known Activations