© 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. 174455
    Prev
    Next
    INDEX
    Explanations

    prize draw

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

    collected, gathered, received information

    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
     Februar
    0.57
     funkc
    0.54
     Dezember
    0.53
    嘜
    0.52
     Ronaldo
    0.50
    teis
    0.50
    te
    0.50
     funções
    0.49
    تس
    0.49
     fevereiro
    0.49
    POSITIVE LOGITS
    WRAP
    0.46
    UMS
    0.45
    "_
    0.44
    ATTER
    0.44
    ANIM
    0.43
    AS
    0.43
    YL
    0.43
    IL
    0.42
    CAST
    0.42
    ₩
    0.42
    Activations Density 0.003%

    No Known Activations