© 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. 128664
    Prev
    Next
    INDEX
    Explanations

    code 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
     irgende
    -0.06
     spør
    -0.06
    居然
    -0.06
     видимо
    -0.06
     terminator
    -0.06
     någon
    -0.06
     რომელი
    -0.06
    ieder
    -0.06
     alguna
    -0.05
     impr
    -0.05
    POSITIVE LOGITS
     require
    0.07
     कैंपस
    0.07
     similarly
    0.06
     ছোট
    0.06
    Require
    0.06
     möj
    0.06
     মাতা
    0.06
     initially
    0.06
     requires
    0.06
     REQUIRE
    0.06
    Activations Density 0.003%

    No Known Activations