© 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. 129059
    Prev
    Next
    INDEX
    Explanations

    legal appellant

    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
     the
    -0.10
     these
    -0.08
     a
    -0.07
     should
    -0.06
    次は
    -0.06
    这些
    -0.06
     an
    -0.06
    erm
    -0.06
    jiang
    -0.06
     Size
    -0.06
    POSITIVE LOGITS
     احد
    0.07
    عرف
    0.07
     আছেন
    0.06
    desde
    0.06
     خاصة
    0.06
    Oklahoma
    0.06
     несмотря
    0.06
     почина
    0.06
    что
    0.06
     начина
    0.06
    Activations Density 0.003%

    No Known Activations