© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13535
    Prev
    Next
    INDEX
    Explanations

    special characters and informal abbreviations

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

    query, task, problem, object type

    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
     be
    0.78
    قة
    0.76
     mise
    0.75
    <0x80>
    0.69
    үй
    0.69
    浗
    0.68
     zwe
    0.68
    鸹
    0.67
     төр
    0.66
    э
    0.66
    POSITIVE LOGITS
    로
    0.86
    ac
    0.84
    aka
    0.78
    ?}
    0.77
    ir
    0.76
    ur
    0.69
    i
    0.69
    ama
    0.68
    in
    0.66
    smtb
    0.66
    Activations Density 0.105%

    No Known Activations