© 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. 57113
    Prev
    Next
    INDEX
    Explanations

    unusual spike

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

    identify specific issues

    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
     Los
    0.54
     In
    0.54
     \
    0.50
     (
    0.49
     whose
    0.48
     in
    0.47
     //
    0.47
     \\
    0.46
    with
    0.45
     ()
    0.45
    POSITIVE LOGITS
    柺
    0.47
    baptism
    0.46
    这个人
    0.46
    mataspid
    0.46
     навіть
    0.45
     балко
    0.45
    兕
    0.44
    unton
    0.43
     البطولة
    0.43
    ᑭ
    0.43
    Activations Density 0.001%

    No Known Activations