© 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. 128553
    Prev
    Next
    INDEX
    Explanations

    criminal trial or offense

    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
    已经
    -0.07
    已經
    -0.07
     AN
    -0.07
    หนัง
    -0.06
     fuel
    -0.06
     використа
    -0.06
     ने
    -0.06
     acorde
    -0.06
    Oak
    -0.06
    вшая
    -0.06
    POSITIVE LOGITS
    分为
    0.06
     продукти
    0.06
     यानी
    0.06
     gradually
    0.06
    itudini
    0.06
     অর্থাৎ
    0.06
     Gradually
    0.06
     saying
    0.06
     come
    0.05
     formal
    0.05
    Activations Density 0.002%

    No Known Activations