© 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. 246666
    Prev
    Next
    INDEX
    Explanations

    specific noun phrases

    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
    試料
    0.55
    H
    0.54
    Lett
    0.50
    デス
    0.49
    BA
    0.48
     ယ
    0.48
    gow
    0.48
    CO
    0.47
    PROTO
    0.47
    C
    0.46
    POSITIVE LOGITS
    ipino
    0.48
    ruppen
    0.46
    ర్ణ
    0.46
    ंगिक
    0.46
    كيت
    0.44
    ర్లు
    0.44
     Handles
    0.42
    ారం
    0.41
    ิจ
    0.41
     angry
    0.40
    Activations Density 0.001%

    No Known Activations