© 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. 115929
    Prev
    Next
    INDEX
    Explanations

    invention or application and relates

    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
     této
    -0.06
     براي
    -0.06
     minist
    -0.06
     tejto
    -0.06
     Otherwise
    -0.06
     tohoto
    -0.06
     المم
    -0.06
     সমস্ত
    -0.06
     cette
    -0.06
     distint
    -0.06
    POSITIVE LOGITS
     consequências
    0.06
     en
    0.06
    !?
    0.06
     etc
    0.06
    በባ
    0.06
     kerana
    0.06
     আটকে
    0.05
    等方面
    0.05
    ামের
    0.05
     places
    0.05
    Activations Density 0.001%

    No Known Activations