© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168411
    Prev
    Next
    INDEX
    Explanations

    legal definitions and terms

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

    documented events and choices

    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
    ላት
    0.54
    ين
    0.52
    ир
    0.50
    passion
    0.50
    е
    0.48
    dataset
    0.48
    love
    0.47
    بيق
    0.46
    hate
    0.46
    и
    0.46
    POSITIVE LOGITS
     追加
    0.48
    পূর্বক
    0.47
     不需要
    0.46
     Maintaining
    0.46
     Became
    0.45
     Ornamental
    0.44
     Rtl
    0.44
     Obtaining
    0.44
     花
    0.43
     Golgi
    0.43
    Activations Density 0.001%

    No Known Activations