© 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. 117106
    Prev
    Next
    INDEX
    Explanations

    code imports and structure

    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
     без
    -0.07
     kiezen
    -0.07
     complètement
    -0.06
     tanpa
    -0.06
    Pocket
    -0.06
     conçu
    -0.06
     ポケット
    -0.06
     완전
    -0.06
     Pocket
    -0.06
     Christi
    -0.06
    POSITIVE LOGITS
    मा
    0.06
    すなわち
    0.06
    Response
    0.06
     iteratively
    0.06
     after
    0.05
     unreasonably
    0.05
    どん
    0.05
    응
    0.05
    栗
    0.05
     the
    0.05
    Activations Density 0.002%

    No Known Activations