© 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. 117598
    Prev
    Next
    INDEX
    Explanations

    announcements, events, holidays

    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
     hohe
    -0.06
     highest
    -0.06
    消防
    -0.06
    商品
    -0.06
     ध
    -0.06
     poorest
    -0.06
     egensk
    -0.06
     average
    -0.05
     Average
    -0.05
     গড়
    -0.05
    POSITIVE LOGITS
    ここでは
    0.07
    ovou
    0.06
    生涯
    0.06
    充满了
    0.06
     triggers
    0.06
     nouvelle
    0.06
     منظ
    0.06
     alone
    0.06
     exiled
    0.06
     szkoły
    0.06
    Activations Density 0.012%

    No Known Activations