© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226967
    Prev
    Next
    INDEX
    Explanations

    body parts and actions

    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
    qu
    0.50
    co
    0.50
    斯
    0.50
    لز
    0.49
    ல்
    0.48
    éral
    0.48
    ्लादेश
    0.48
    ład
    0.47
    ixon
    0.47
    n
    0.47
    POSITIVE LOGITS
     notifier
    0.46
     沈
    0.45
     дверей
    0.45
     planner
    0.43
    ﹕
    0.43
     queued
    0.42
     scrolled
    0.42
     sureties
    0.41
     assures
    0.41
    恚
    0.40
    Activations Density 0.000%

    No Known Activations