© 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. 6617
    Prev
    Next
    INDEX
    Explanations

    the country

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

    Title and headlines

    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
    [
    0.47
    工作
    0.46
    o
    0.44
     bởi
    0.43
     Bhan
    0.43
     independently
    0.42
    (*
    0.42
     importantes
    0.42
     Hutchinson
    0.42
     Outcomes
    0.42
    POSITIVE LOGITS
     mètre
    0.55
     personagem
    0.54
    '`--
    0.52
     เหรอ
    0.52
     ശിഷ്യ
    0.51
    เค
    0.51
    äck
    0.50
     personnage
    0.50
     മാര്‍
    0.50
     بنابراین
    0.50
    Activations Density 0.000%

    No Known Activations