© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31393
    Prev
    Next
    INDEX
    Explanations

    Microsoft Windows websites hosting

    np_acts-logits-general · gemini-2.5-flash-lite

    sexually suggestive conversations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFT
    0.48
     końcu
    0.47
     produção
    0.46
     τέ
    0.46
    徕
    0.46
     ק
    0.45
    larını
    0.45
     işlemi
    0.45
    istä
    0.45
     நிமிட
    0.45
    POSITIVE LOGITS
     confining
    0.44
    javaHome
    0.39
     stringent
    0.39
    .
    0.39
     agreeable
    0.37
    hamed
    0.37
     moneys
    0.37
     mandat
    0.37
    ائن
    0.36
    ুদ
    0.36
    Activations Density 0.000%

    No Known Activations