© 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. 5435
    Prev
    Next
    INDEX
    Explanations

    following closing parenthesis or colon

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

    (s) followed by ) or :

    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
    ඖ
    0.42
    ૉ
    0.42
    ్యా
    0.41
    бен
    0.41
    릅
    0.41
    ographics
    0.41
    쯤
    0.41
    িন্ন
    0.40
    游戏中
    0.40
    osexual
    0.39
    POSITIVE LOGITS
    io
    0.58
    he
    0.54
    definition
    0.51
     disponible
    0.50
    ative
    0.50
    re
    0.50
    i
    0.50
    has
    0.49
    この
    0.49
     principali
    0.49
    Activations Density 0.001%

    No Known Activations