© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 128295
    Prev
    Next
    INDEX
    Explanations

    command keywords and settings

    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
     by
    -0.09
     of
    -0.07
     from
    -0.07
     first
    -0.06
     could
    -0.06
     on
    -0.06
     cambiar
    -0.06
    صير
    -0.06
    ردو
    -0.06
     von
    -0.06
    POSITIVE LOGITS
    Similarly
    0.07
    有的
    0.06
    夲
    0.06
    ؛
    0.06
     mesmo
    0.06
    有些
    0.05
     differenza
    0.05
    一般来说
    0.05
     една
    0.05
     eftersom
    0.05
    Activations Density 0.007%

    No Known Activations