© 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. 116066
    Prev
    Next
    INDEX
    Explanations

    payment methods

    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
    вейца
    -0.07
    interactive
    -0.06
    監督
    -0.06
     फीसदी
    -0.06
     retailing
    -0.06
    软件包
    -0.06
     controlado
    -0.06
    告知
    -0.06
    spaceBetween
    -0.06
     alphanumeric
    -0.06
    POSITIVE LOGITS
     will
    0.07
     to
    0.06
     چون
    0.06
    㑨
    0.06
    効率
    0.06
     কখনই
    0.06
    Log
    0.06
     distinguishing
    0.06
     श्रद्धालु
    0.06
     trying
    0.06
    Activations Density 0.007%

    No Known Activations