© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129971
    Prev
    Next
    INDEX
    Explanations

    change customization modification

    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
    mult
    -0.07
    Mult
    -0.06
    an
    -0.06
     multi
    -0.06
     इकट्ठा
    -0.06
    Auto
    -0.06
    ुल
    -0.06
     an
    -0.06
     multipl
    -0.06
    MULT
    -0.06
    POSITIVE LOGITS
     заменить
    0.08
     nogle
    0.07
     didn
    0.07
    Roasted
    0.07
     Substituting
    0.07
     roasted
    0.06
     δεν
    0.06
     indelible
    0.06
     instead
    0.06
     specify
    0.06
    Activations Density 0.200%

    No Known Activations