© 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. 120979
    Prev
    Next
    INDEX
    Explanations

    matching color or style

    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
     results
    -0.07
    입니다
    -0.07
     kantor
    -0.07
    results
    -0.06
     зво
    -0.06
     Bear
    -0.06
     résumé
    -0.06
     Results
    -0.06
    ลด
    -0.06
     الجرس
    -0.06
    POSITIVE LOGITS
     işlet
    0.07
     Might
    0.06
    Might
    0.06
    啥
    0.06
     Samoa
    0.06
     って
    0.06
    TOP
    0.06
     ഓരോ
    0.06
     what
    0.06
    Master
    0.05
    Activations Density 0.005%

    No Known Activations