© 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. 118693
    Prev
    Next
    INDEX
    Explanations

    data processing and analysis

    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
     which
    -0.08
     których
    -0.07
     должно
    -0.06
     sư
    -0.06
     хотя
    -0.06
     sollte
    -0.06
     should
    -0.06
     möglichst
    -0.06
     Although
    -0.06
    虽然
    -0.06
    POSITIVE LOGITS
     makeshift
    0.07
     protection
    0.07
    protection
    0.07
    Protection
    0.07
     защиты
    0.07
     Protection
    0.06
    ^{-}\
    0.06
    耐
    0.06
     terve
    0.06
     coupon
    0.06
    Activations Density 0.005%

    No Known Activations