© 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. 94507
    Prev
    Next
    INDEX
    Explanations

    simple and quick for groups

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

    translating idioms, concepts

    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
    You
    0.54
     Tune
    0.50
    Ссы
    0.48
    पत्र
    0.48
    ת
    0.47
     Diffraction
    0.47
    পথ
    0.46
    تون
    0.46
    Photon
    0.46
    voy
    0.46
    POSITIVE LOGITS
     sustainably
    0.52
     expedit
    0.50
     ラック
    0.48
     इसने
    0.48
     expedited
    0.46
     swiftly
    0.46
     eroded
    0.46
     店
    0.45
     były
    0.45
     sustainable
    0.45
    Activations Density 0.001%

    No Known Activations