© 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. 116910
    Prev
    Next
    INDEX
    Explanations

    jQuery methods and actions

    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
     imperfect
    -0.08
     مسئله
    -0.07
     caderno
    -0.07
    祹
    -0.06
    聒
    -0.06
    镉
    -0.06
    ရား
    -0.06
     naturaleza
    -0.06
     lavorare
    -0.06
     идеа
    -0.06
    POSITIVE LOGITS
     could
    0.06
    ej
    0.06
    vamos
    0.06
    สนใจ
    0.06
     equivalent
    0.05
    geny
    0.05
    お得
    0.05
    *.
    0.05
     samtidigt
    0.05
     Epidemi
    0.05
    Activations Density 0.015%

    No Known Activations