© 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. 108097
    Prev
    Next
    INDEX
    Explanations

    on followed by months

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

    leader, pivot, posts, source, Stoa

    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
    avait
    0.50
     apparaît
    0.50
     choisi
    0.49
    ꞎ
    0.49
     léz
    0.48
    és
    0.47
     paramInt
    0.47
     résult
    0.46
    竻
    0.46
     prête
    0.46
    POSITIVE LOGITS
     Airports
    0.52
    BAI
    0.46
    Ak
    0.45
    .,
    0.45
     in
    0.45
    Cap
    0.45
     в
    0.44
     Afgan
    0.43
    Richard
    0.43
     Hartford
    0.43
    Activations Density 0.001%

    No Known Activations