© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123075
    Prev
    Next
    INDEX
    Explanations

    shapes expectations

    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
     Boolean
    0.42
     ‘
    0.40
     去
    0.38
     緑
    0.38
     `
    0.38
     Menu
    0.38
     Floating
    0.38
     Monetary
    0.37
     Voting
    0.37
    新しい
    0.37
    POSITIVE LOGITS
    陴
    0.46
     procedimentos
    0.43
     instill
    0.42
     комплект
    0.42
    llabus
    0.41
     تجه
    0.41
     канцеля
    0.41
     оборудования
    0.41
     perju
    0.40
    掙
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.