© 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. 148799
    Prev
    Next
    INDEX
    Explanations

    links and fulfillment

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

    extensive

    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
    ного
    0.59
    щения
    0.54
    ться
    0.50
    телями
    0.48
    akam
    0.48
    Gesture
    0.48
    汙
    0.47
    hrm
    0.46
    тели
    0.45
    лығы
    0.45
    POSITIVE LOGITS
     n
    0.56
     න
    0.48
     न
    0.46
     Achilles
    0.46
     smokers
    0.45
     covenants
    0.45
     Al
    0.45
     ක්ර
    0.44
     ن
    0.44
     ட
    0.44
    Activations Density 0.000%

    No Known Activations