© 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. 40-GEMMASCOPE-2-RES-65K
    7. 4472
    Prev
    Next
    INDEX
    Explanations

    future actions and statements

    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
    Negative Logits
    a
    0.59
    Typically
    0.55
    Util
    0.54
    Exam
    0.52
    One
    0.49
    Though
    0.49
    A
    0.48
    У
    0.48
    Up
    0.47
    Table
    0.46
    POSITIVE LOGITS
     obeyed
    0.54
     XNUMX
    0.54
     arouse
    0.53
    ḫ
    0.52
     trembled
    0.51
     dreamed
    0.50
     avenge
    0.50
     secretly
    0.50
    ҷ
    0.50
     seduce
    0.49
    Activations Density 0.029%

    No Known Activations