© 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. 119664
    Prev
    Next
    INDEX
    Explanations

    dates, times, and capitalized names

    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
     keselamatan
    -0.07
    useppe
    -0.07
     শুধু
    -0.06
    imetable
    -0.06
    ိတ်
    -0.06
     خونه
    -0.06
     megfelelő
    -0.06
     ამ
    -0.06
     möglichst
    -0.06
     exceedingly
    -0.06
    POSITIVE LOGITS
     diaria
    0.06
     feasible
    0.06
    шы
    0.06
    ऊ
    0.06
    instead
    0.06
     bref
    0.05
     रोशन
    0.05
    scientific
    0.05
     fondness
    0.05
    虽
    0.05
    Activations Density 0.001%

    No Known Activations