© 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. 92125
    Prev
    Next
    INDEX
    Explanations

    science, methods, and technical jargon

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

    operations on parallel collections

    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
     Кон
    0.54
    読む
    0.50
     приват
    0.49
     Виктор
    0.49
     ремонт
    0.48
     ادي
    0.48
    폈
    0.48
     формування
    0.47
     относительно
    0.47
     Германия
    0.47
    POSITIVE LOGITS
    empor
    0.43
    OM
    0.42
    MOT
    0.42
     đôi
    0.42
    ges
    0.41
    oretical
    0.41
    方
    0.41
    ABA
    0.41
    ム
    0.41
    给
    0.41
    Activations Density 0.000%

    No Known Activations