© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115635
    Prev
    Next
    INDEX
    Explanations

    booking information, impossible, government, we take, on PAS, this is, this project, an additional, consistently, not haul

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

    lists of items or sections

    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
    emers
    0.50
    ée
    0.49
    (
    0.46
     religiosos
    0.45
    eties
    0.45
    à
    0.44
    大众
    0.44
    ò
    0.44
    了
    0.43
    Forgot
    0.43
    POSITIVE LOGITS
     playroom
    0.63
     toner
    0.57
     speedboat
    0.57
     diaper
    0.54
     stair
    0.54
     ligation
    0.54
     water
    0.53
     farmland
    0.53
     confectionery
    0.52
     crease
    0.51
    Activations Density 0.001%

    No Known Activations