© 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. 237625
    Prev
    Next
    INDEX
    Explanations

    time off

    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
    팸
    0.57
    customers
    0.50
    кину
    0.50
    LOW
    0.49
    bigger
    0.47
     쇼
    0.47
    RICK
    0.47
    Customers
    0.46
    ᴼ
    0.46
    employed
    0.45
    POSITIVE LOGITS
     guest
    0.52
     symmetric
    0.51
     justice
    0.49
     necessary
    0.48
     temporary
    0.47
    imizi
    0.46
     descent
    0.46
     Bose
    0.44
     handicapped
    0.44
     main
    0.44
    Activations Density 0.001%

    No Known Activations