© 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. 139717
    Prev
    Next
    INDEX
    Explanations

    compartment dissection

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

    platform Azure, Beer Tasting, General Purpose

    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
    s
    0.52
    gies
    0.49
     Diagrams
    0.47
    gx
    0.47
    models
    0.45
    y
    0.44
    gk
    0.43
    !)
    0.43
    c
    0.43
    样
    0.43
    POSITIVE LOGITS
     sábado
    0.53
     jogador
    0.52
     secretário
    0.52
     intérpre
    0.50
     horde
    0.50
     duż
    0.49
     sprzedaży
    0.49
     penurunan
    0.48
    טן
    0.48
     আই
    0.47
    Activations Density 0.000%

    No Known Activations