© 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. 128057
    Prev
    Next
    INDEX
    Explanations

    StartAction Project

    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
     सोड
    -0.07
     some
    -0.06
     hizo
    -0.06
     Bs
    -0.06
     alcune
    -0.06
     الرئيسي
    -0.06
     থাকলেও
    -0.06
     கொடுக்க
    -0.06
    дной
    -0.06
     nuova
    -0.06
    POSITIVE LOGITS
    つまり
    0.06
    parse
    0.06
    私の
    0.06
    する場合
    0.06
     yönt
    0.06
    ឬ
    0.06
    我的
    0.06
     제가
    0.06
     puertas
    0.06
    我又
    0.06
    Activations Density 0.007%

    No Known Activations