© 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. 2484
    Prev
    Next
    INDEX
    Explanations

    or equivalent

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

    essential for

    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
    힐
    0.49
     избра
    0.46
     устро
    0.45
    期間
    0.43
    、《
    0.43
    走
    0.43
    理論
    0.43
     공개
    0.43
    楽天
    0.42
    師
    0.42
    POSITIVE LOGITS
     hatta
    0.57
     kik
    0.53
    as
    0.50
     Lucille
    0.49
    因为它
    0.49
     asla
    0.49
     deed
    0.48
     după
    0.48
    ceral
    0.48
    selt
    0.47
    Activations Density 0.000%

    No Known Activations