© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 145277
    Prev
    Next
    INDEX
    Explanations

    in theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    c
    0.93
    es
    0.86
    ate
    0.81
    ed
    0.79
    س
    0.78
    im
    0.78
    th
    0.77
    '
    0.77
    m
    0.75
    v
    0.73
    POSITIVE LOGITS
     continuité
    0.69
     UBND
    0.67
    DrvGPIO
    0.64
    überküloz
    0.64
    UserProg
    0.62
     autorización
    0.62
     уйнау
    0.62
     Некоторые
    0.62
    gunaan
    0.62
    Leftrightarrow
    0.61
    Activations Density 0.004%

    No Known Activations