© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116037
    Prev
    Next
    INDEX
    Explanations

    Notary, Apostille, usage, convention

    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
    Negative Logits
     planning
    -0.06
     देंगे
    -0.06
     informativa
    -0.06
     timetable
    -0.06
    undang
    -0.06
     planing
    -0.06
    planning
    -0.06
     homolog
    -0.06
    Lord
    -0.06
     তালিক
    -0.06
    POSITIVE LOGITS
     использования
    0.07
     استخدم
    0.07
     penggunaan
    0.07
     χρησιμοποι
    0.07
     استفاده
    0.06
     használ
    0.06
     использовании
    0.06
     conventionally
    0.06
     benutzt
    0.06
     use
    0.06
    Activations Density 0.005%

    No Known Activations