© 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. 141364
    Prev
    Next
    INDEX
    Explanations

    actions, consequences, or details

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

    levels & types

    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
    Negative Logits
     Snowflake
    0.47
     Bib
    0.47
     completion
    0.46
     ¹
    0.46
     re
    0.46
     Utopia
    0.46
     î
    0.45
    0.45
     fireplaces
    0.44
     complaint
    0.44
    POSITIVE LOGITS
    sizeof
    0.52
     embarazada
    0.50
    truncate
    0.48
    সমাজ
    0.48
    trunc
    0.47
    esquerdo
    0.47
    的选择
    0.47
    setProperty
    0.47
    정에
    0.46
    ్లా
    0.46
    Activations Density 0.001%

    No Known Activations