© 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. 205718
    Prev
    Next
    INDEX
    Explanations

    medical, legal, and diverse entities

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

    not statements and clarifications

    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
    望
    0.49
    મ
    0.48
    Бан
    0.46
    生意
    0.46
     яхшы
    0.44
    SUCCESS
    0.44
    му
    0.44
    Earlier
    0.43
    quito
    0.42
    ถ
    0.42
    POSITIVE LOGITS
     calendrier
    0.61
     チェ
    0.54
     Datenschutz
    0.52
     Hills
    0.52
     韓国
    0.50
     Korea
    0.49
     تعیین
    0.49
     では
    0.49
     Preference
    0.49
     フランス
    0.49
    Activations Density 0.001%

    No Known Activations