© 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. 142775
    Prev
    Next
    INDEX
    Explanations

    docking reports updated

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

    fútbol americano

    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
     gerekir
    0.59
     suya
    0.53
    rasında
    0.52
     indicada
    0.50
     blanca
    0.50
     utilizada
    0.49
     branca
    0.49
     (-
    0.49
     işlemi
    0.48
    ?!?
    0.48
    POSITIVE LOGITS
    શ્વ
    0.45
     dock
    0.44
    sectors
    0.44
     Dock
    0.44
    dock
    0.44
    atth
    0.43
    阐
    0.41
     docking
    0.41
    fans
    0.40
    Dock
    0.40
    Activations Density 0.001%

    No Known Activations