© 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. 106332
    Prev
    Next
    INDEX
    Explanations

    visual particles

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

    ADAS function status, double dash

    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
    ጥረ
    0.50
    ‘
    0.49
     pengend
    0.46
     ahorita
    0.46
     Menteri
    0.46
     jasno
    0.45
     Gemeinde
    0.45
     Analyst
    0.45
     Atención
    0.45
    ሔ
    0.45
    POSITIVE LOGITS
    ylim
    0.52
    Native
    0.49
     copp
    0.48
    approx
    0.48
    prod
    0.47
    underbrace
    0.45
    HttpPost
    0.45
    kyo
    0.45
     தோ
    0.45
    iliy
    0.44
    Activations Density 0.000%

    No Known Activations