© 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. 139768
    Prev
    Next
    INDEX
    Explanations

    gallon jug with

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

    local surroundings

    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
     Jays
    0.51
    veh
    0.47
     Beale
    0.46
     eth
    0.46
     Frisch
    0.46
    Benzoimidazol
    0.45
     Lash
    0.45
     [&
    0.45
     tolerable
    0.45
    uroy
    0.44
    POSITIVE LOGITS
     televisão
    0.50
    Ci
    0.49
     vitória
    0.47
    Otros
    0.47
    resident
    0.46
    Appearance
    0.46
     অধি
    0.46
    เมื่อ
    0.46
    テレビ
    0.46
    vrd
    0.46
    Activations Density 0.000%

    No Known Activations