© 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. 193133
    Prev
    Next
    INDEX
    Explanations

    August, delete, plus, still

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

    programming concepts and content sources

    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
    ratio
    0.45
     retir
    0.44
     quedó
    0.43
     chemot
    0.42
     neoplasms
    0.41
     ಅನುಪ
    0.41
    oldCount
    0.40
     香
    0.40
     alkaloids
    0.40
    varrho
    0.40
    POSITIVE LOGITS
     Blade
    0.45
    '<
    0.45
     Barça
    0.44
     Burnley
    0.44
     Reykjavik
    0.44
     Execute
    0.43
     towering
    0.43
     Barcelona
    0.43
    세를
    0.42
     Institutes
    0.42
    Activations Density 0.002%

    No Known Activations