© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119341
    Prev
    Next
    INDEX
    Explanations

    offspring

    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
     unequivocally
    -0.07
     절대
    -0.07
     지역
    -0.07
     exager
    -0.07
    當地
    -0.07
     contextual
    -0.07
     되겠
    -0.06
     கல்விய
    -0.06
    変わ
    -0.06
    🦋
    -0.06
    POSITIVE LOGITS
    Various
    0.07
     приобре
    0.06
     various
    0.06
    various
    0.06
     during
    0.06
    new
    0.06
     ҷ
    0.06
     Various
    0.06
     هنگام
    0.06
     crystall
    0.06
    Activations Density 0.003%

    No Known Activations