© 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. 134261
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases, often ending sentences

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

    parenthetical qualifiers

    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
    t
    1.05
    a
    0.90
    an
    0.87
    in
    0.84
    s
    0.79
    type
    0.71
    $,
    0.71
    $.
    0.69
    ه
    0.68
    tahun
    0.68
    POSITIVE LOGITS
    ين
    0.87
    ض
    0.66
    ди
    0.65
     quadrados
    0.64
    اسية
    0.64
    зи
    0.63
     cá
    0.63
    يح
    0.62
    لم
    0.61
    quele
    0.59
    Activations Density 0.132%

    No Known Activations