© 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. 85860
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements

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

    authority established, afternoon

    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
    лиги
    0.48
    ї
    0.48
    но
    0.47
    รายการ
    0.47
     dast
    0.47
    ль
    0.47
     mogli
    0.46
    をはじめ
    0.46
    स
    0.45
    ਾਲ
    0.45
    POSITIVE LOGITS
     Blend
    0.53
     Calibration
    0.53
     Ammonia
    0.52
     Goethe
    0.51
     phenolic
    0.50
     Resid
    0.49
     Dopo
    0.49
     Ammonium
    0.48
     Goat
    0.48
     Σε
    0.48
    Activations Density 0.003%

    No Known Activations