© 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. 218201
    Prev
    Next
    INDEX
    Explanations

    Phi Delta Kappa International

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

    means or against counseling

    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
    Not in Any Lists

    No Comments

    Negative Logits
     дві
    0.52
    д
    0.50
     모델
    0.50
     вигляді
    0.50
     새벽
    0.48
    ен
    0.47
     бі
    0.47
    setAuto
    0.47
     моделей
    0.47
     alloying
    0.46
    POSITIVE LOGITS
     Transportation
    0.53
    '
    0.53
     Conservancy
    0.47
    Sheila
    0.47
    Quota
    0.47
     gubern
    0.45
     transatlantic
    0.45
    スマ
    0.44
     Development
    0.44
    Development
    0.43
    Activations Density 0.000%

    No Known Activations