© 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. 112808
    Prev
    Next
    INDEX
    Explanations

    chart

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

    chart, charting, cartographer

    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
    ع
    0.57
    ן
    0.52
    尧
    0.48
     কলকাত
    0.47
    elapsed
    0.46
    kc
    0.46
    憶
    0.45
    𝐸
    0.45
    jk
    0.44
    ILTON
    0.44
    POSITIVE LOGITS
     charts
    0.93
     charting
    0.87
    Chart
    0.86
     charted
    0.86
     Chart
    0.83
     chart
    0.82
     Charts
    0.82
    charts
    0.77
     Cart
    0.75
     cart
    0.73
    Activations Density 0.095%

    No Known Activations