© 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. 110044
    Prev
    Next
    INDEX
    Explanations

    canyon, plan, order

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

    common misconfigurations

    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
    '
    0.43
    只能
    0.41
    ＰＥ
    0.41
     насто
    0.41
    ^{+}(
    0.40
    cl
    0.40
    运营
    0.40
    恐
    0.40
    崇
    0.40
     Plots
    0.40
    POSITIVE LOGITS
     świata
    0.57
     світу
    0.57
     egz
    0.50
    ış
    0.50
     Jerman
    0.49
    ön
    0.47
    ീക
    0.46
     প্রান্ত
    0.46
     świecie
    0.46
    tFileInputExcel
    0.46
    Activations Density 0.000%

    No Known Activations