© 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. 130302
    Prev
    Next
    INDEX
    Explanations

    pertussis

    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
     sun
    -0.07
    此外
    -0.06
    ಎಂ
    -0.06
     Seasons
    -0.06
     क्षेत्रीय
    -0.06
    countries
    -0.06
     tropical
    -0.06
     Ս
    -0.06
     geográfica
    -0.06
     isotonic
    -0.06
    POSITIVE LOGITS
     நிறைந்த
    0.06
     KIND
    0.06
     फ्रेंड्स
    0.06
    讲话
    0.05
     även
    0.05
     recuerda
    0.05
     स्मरण
    0.05
    Talk
    0.05
    කින්
    0.05
    🤫
    0.05
    Activations Density 0.009%

    No Known Activations