© 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. 190367
    Prev
    Next
    INDEX
    Explanations

    advertising, fee, developed, used, team, controller

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

    offers support or positive intent

    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
    x
    0.70
    u
    0.62
    n
    0.60
    i
    0.59
    h
    0.58
    or
    0.57
    ar
    0.57
    !
    0.55
    c
    0.54
    o
    0.53
    POSITIVE LOGITS
     температура
    0.55
     ጥሩ
    0.55
     провин
    0.53
     точке
    0.52
     часто
    0.52
     Biasanya
    0.52
     краї
    0.51
     ঝাঁপ
    0.50
     месяца
    0.49
    笆
    0.49
    Activations Density 0.001%

    No Known Activations