© 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. 179469
    Prev
    Next
    INDEX
    Explanations

    Mercury glass stars

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

    flow, culture, ice, since, clarify, component

    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
    a
    0.56
    S
    0.53
     subray
    0.50
    s
    0.48
    meg
    0.48
    as
    0.48
     metaf
    0.46
    y
    0.45
     systemat
    0.45
     S
    0.45
    POSITIVE LOGITS
     कारण
    0.53
     जरूरी
    0.50
     đặc
    0.50
    ול
    0.48
     enjoying
    0.48
     cộng
    0.48
    정이
    0.47
     можливість
    0.46
     ধৈর্য
    0.46
     Đảng
    0.46
    Activations Density 0.000%

    No Known Activations