© 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. 227778
    Prev
    Next
    INDEX
    Explanations

    disputed domain names or purchasing shares

    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
     dreaded
    0.46
    咔
    0.44
    trying
    0.43
    尝试
    0.43
    upid
    0.42
    츰
    0.42
     тока
    0.42
    谶
    0.41
    édéric
    0.41
     phospholipids
    0.40
    POSITIVE LOGITS
     from
    0.47
     є
    0.46
    brun
    0.44
    スタンド
    0.44
     Brun
    0.43
     parabol
    0.43
    ̨
    0.43
     सुद्धा
    0.43
     permettent
    0.42
    ریف
    0.42
    Activations Density 0.001%

    No Known Activations