© 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. 129160
    Prev
    Next
    INDEX
    Explanations

    event handlers

    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
     prevailed
    -0.07
     dined
    -0.07
     poput
    -0.07
     prepared
    -0.06
     গার
    -0.06
     করছে
    -0.06
     destined
    -0.06
    higher
    -0.06
     destinado
    -0.06
     higher
    -0.06
    POSITIVE LOGITS
     (
    0.07
     and
    0.06
    要
    0.06
    是
    0.06
     menu
    0.05
    lyn
    0.05
    kon
    0.05
     ব্যাব
    0.05
    。
    0.05
    คู่
    0.05
    Activations Density 0.001%

    No Known Activations