© 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. 141888
    Prev
    Next
    INDEX
    Explanations

    County, fines, orders, migrate

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

    causing unintended

    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
    ë
    0.44
    ravel
    0.42
    尽可能
    0.42
    吊
    0.42
    ύν
    0.42
    积累
    0.42
    ुर
    0.40
    рье
    0.40
    传播
    0.40
    /
    0.40
    POSITIVE LOGITS
    GON
    0.55
     Ain
    0.52
     Mahesh
    0.51
     Dez
    0.50
    Authenticated
    0.50
     DER
    0.50
     Esp
    0.50
    Ain
    0.49
    Gand
    0.49
     China
    0.48
    Activations Density 0.000%

    No Known Activations