© 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. 39366
    Prev
    Next
    INDEX
    Explanations

    confusing or around

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

    names describing people/organizations

    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
    il
    0.48
     žene
    0.48
    xen
    0.47
    ilí
    0.47
     Penang
    0.47
    нию
    0.46
    rows
    0.46
    ║
    0.46
    bri
    0.46
    mayan
    0.46
    POSITIVE LOGITS
    ⺀
    0.53
    检察
    0.52
    輋
    0.52
     investig
    0.50
    [
    0.50
    ถมศึกษา
    0.49
     comments
    0.48
     das
    0.48
    拔
    0.47
     career
    0.47
    Activations Density 0.000%

    No Known Activations