© 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. 63576
    Prev
    Next
    INDEX
    Explanations

    numbers and categories

    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
     €.
    0.47
     Bavaria
    0.47
     ■
    0.44
    0.44
     *.
    0.43
     Andreas
    0.43
     Moritz
    0.43
     ä
    0.42
     /
    0.42
     valable
    0.42
    POSITIVE LOGITS
    неоп
    0.50
    ências
    0.49
    ЕВ
    0.48
    MODIFY
    0.47
    ೇಶ್
    0.47
    於
    0.47
    যখন
    0.46
    TEAM
    0.46
    مدينة
    0.46
    どこ
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.