© 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. 129436
    Prev
    Next
    INDEX
    Explanations

    directives or official titles

    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
     diagnosis
    -0.07
    但在
    -0.06
     diagnoses
    -0.06
     opérés
    -0.06
     Product
    -0.06
     Individual
    -0.06
     राग
    -0.06
     हेतु
    -0.06
    品番
    -0.06
     individualized
    -0.06
    POSITIVE LOGITS
     seizing
    0.07
     لقب
    0.06
     traer
    0.06
     séance
    0.06
     establishing
    0.06
     seemingly
    0.06
     cellulose
    0.06
     descoper
    0.06
     धावा
    0.06
    ader
    0.06
    Activations Density 0.001%

    No Known Activations