© 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. 87267
    Prev
    Next
    INDEX
    Explanations

    dynamic or static states

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

    dynamic content, behavior, pricing

    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
    ,
    0.56
     RAIL
    0.56
     toasted
    0.54
     taxed
    0.52
    -
    0.52
    I
    0.52
     setInterval
    0.51
     straighten
    0.50
    ymy
    0.50
    ^-
    0.49
    POSITIVE LOGITS
    动态
    1.05
     динами
    1.02
    dynamic
    1.02
    DYNAMIC
    0.95
     dynamically
    0.95
     dynamic
    0.91
     dinâmica
    0.88
    動
    0.88
    静态
    0.87
     गतिशील
    0.87
    Activations Density 0.122%

    No Known Activations