© 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-16K
    7. 12577
    Prev
    Next
    INDEX
    Explanations

    end of list or clause

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

    words within parentheses

    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_16k_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
     (
    0.96
     （
    0.89
     ("
    0.71
    ни
    0.71
     (<
    0.71
    (
    0.70
     كه
    0.69
     μπορεί
    0.65
     сцен
    0.64
     (“
    0.63
    POSITIVE LOGITS
    a
    0.95
    i
    0.79
    _
    0.73
    د
    0.70
    es
    0.70
    as
    0.70
    ek
    0.70
    io
    0.68
    o
    0.68
    u
    0.68
    Activations Density 0.607%

    No Known Activations