© 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. 127402
    Prev
    Next
    INDEX
    Explanations

    Surface Dial

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

    beyond simplyhabit formationpurpose definitiongenerates content

    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
     remarqué
    0.52
     resorption
    0.51
     detr
    0.49
     évident
    0.47
     당연
    0.46
    득
    0.46
     suppressor
    0.45
    了很多
    0.45
     demonstrable
    0.44
    ං
    0.44
    POSITIVE LOGITS
    ড়ো
    0.50
    FI
    0.47
    Square
    0.47
     Bry
    0.46
    Dol
    0.46
    Gall
    0.46
     Cull
    0.45
    Powell
    0.45
    Coleman
    0.45
    *",
    0.45
    Activations Density 0.001%

    No Known Activations