© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50389
    Prev
    Next
    INDEX
    Explanations

    Nicole Eggert followed by Egg

    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_40_width_65k_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
    슥
    0.42
     axiomatic
    0.40
    Naming
    0.40
     HEARING
    0.40
     ಒ
    0.39
     usurp
    0.39
    Hashing
    0.38
     AUTHORITY
    0.37
    ഢ
    0.37
     ajout
    0.37
    POSITIVE LOGITS
     columns
    0.73
     column
    0.66
    column
    0.61
     Columns
    0.60
    columns
    0.59
    Columns
    0.58
     Column
    0.56
     columnas
    0.55
     दो
    0.53
     колон
    0.53
    Activations Density 0.012%

    No Known Activations