© 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. 238321
    Prev
    Next
    INDEX
    Explanations

    App, Dw, data, Osaka, fully, dark, telling, certain

    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
    柄
    0.52
    编制
    0.49
     deterioration
    0.47
     squadrons
    0.46
     squadron
    0.45
    흘
    0.45
    美丽
    0.45
    指標
    0.44
    ITEM
    0.44
    ต
    0.44
    POSITIVE LOGITS
     quiere
    0.50
     intimidated
    0.50
     شرکت
    0.49
    bitwise
    0.49
     subtração
    0.48
     akibat
    0.48
    ut
    0.48
    unud
    0.47
    am
    0.46
    hta
    0.46
    Activations Density 0.001%

    No Known Activations