© 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. 120808
    Prev
    Next
    INDEX
    Explanations

    liquids, based, heated

    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
    Not in Any Lists

    No Comments

    Negative Logits
    :
    -0.08
     also
    -0.07
    ;
    -0.07
    에도
    -0.06
     how
    -0.06
    also
    -0.06
     другое
    -0.06
    ,
    -0.06
     (
    -0.06
     अपनी
    -0.06
    POSITIVE LOGITS
    AndWait
    0.07
    Often
    0.06
    ⁤
    0.06
    Sometimes
    0.06
    DialogWhen
    0.06
     Often
    0.06
     yaklaşık
    0.06
    প্রায়
    0.06
     Sometimes
    0.06
     часто
    0.06
    Activations Density 0.009%

    No Known Activations