© 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. 118038
    Prev
    Next
    INDEX
    Explanations

    x86 architecture

    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
    diabetes
    -0.06
    नून
    -0.06
     seven
    -0.06
     الجهاز
    -0.06
     diabetes
    -0.06
     sober
    -0.06
     too
    -0.06
     aka
    -0.06
     organs
    -0.06
     ocho
    -0.06
    POSITIVE LOGITS
     entire
    0.06
     domést
    0.06
     Valerie
    0.06
    entire
    0.06
    理由
    0.06
    最新
    0.06
     чём
    0.06
    anie
    0.06
    ச்
    0.06
     možné
    0.06
    Activations Density 0.002%

    No Known Activations