© 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. 233053
    Prev
    Next
    INDEX
    Explanations

    miscarriage rates, proxy materials

    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
    etc
    0.53
     slew
    0.51
    지
    0.50
    in
    0.49
    on
    0.49
    1
    0.47
    make
    0.47
    Э
    0.47
    жи
    0.46
    ні
    0.46
    POSITIVE LOGITS
     الاطلاع
    0.52
     ਕੋ
    0.51
    lexeme
    0.50
     Hinduism
    0.49
     الجنس
    0.49
    uintes
    0.47
     സമ
    0.47
     Distrito
    0.47
     الإلكتر
    0.47
     sexu
    0.46
    Activations Density 0.001%

    No Known Activations