© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212056
    Prev
    Next
    INDEX
    Explanations

    yun yung

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

    composition of elements

    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
    Negative Logits
    აში
    0.48
     Puritan
    0.47
     rumble
    0.45
    illerie
    0.42
    ӓ
    0.42
     Коми
    0.42
    ა
    0.40
     우
    0.40
    sprites
    0.40
     Dearborn
    0.40
    POSITIVE LOGITS
     Doesn
    0.48
    Didn
    0.47
    Doesn
    0.47
    ନ୍
    0.46
    metric
    0.45
     результат
    0.45
     résultat
    0.45
    皆さん
    0.45
    没错
    0.45
    we
    0.44
    Activations Density 0.000%

    No Known Activations