© 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. 161881
    Prev
    Next
    INDEX
    Explanations

    throne twice

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

    execute effectively, no wires, bring joy

    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
     svě
    0.53
     sozial
    0.50
    不愿意
    0.49
     appellate
    0.45
     *);
    0.44
    $=
    0.44
    不敢
    0.44
    稻
    0.44
    সংখ্যক
    0.43
     פּ
    0.43
    POSITIVE LOGITS
    uteurs
    0.58
    می
    0.54
    يها
    0.48
    ributions
    0.46
    ர்ச்ச
    0.46
    OHA
    0.46
    رود
    0.45
    ALK
    0.45
    ری
    0.44
    ود
    0.44
    Activations Density 0.000%

    No Known Activations