© 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. 116834
    Prev
    Next
    INDEX
    Explanations

    long or lengthy descriptions

    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
     extravagant
    -0.07
     consuming
    -0.07
     tremendous
    -0.06
     exhaustive
    -0.06
     fierce
    -0.06
    óloga
    -0.06
     completo
    -0.06
     intense
    -0.06
     intensa
    -0.06
     rousing
    -0.06
    POSITIVE LOGITS
     فقط
    0.07
    簡單
    0.06
     ন্যা
    0.06
     неболь
    0.06
     மூன்று
    0.06
     kleine
    0.06
     간단
    0.06
     recognises
    0.06
    BottomSheet
    0.06
    ลาย
    0.06
    Activations Density 0.015%

    No Known Activations