© 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. 134264
    Prev
    Next
    INDEX
    Explanations

    data values, columns, XML, JSON

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

    pandas dataframe operations

    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
     nonEmpty
    0.54
     ważne
    0.52
    Tempo
    0.48
    虽
    0.47
    🕑
    0.46
    悭
    0.46
    ząd
    0.46
     长
    0.46
    تری
    0.46
    ัติ
    0.45
    POSITIVE LOGITS
    fillna
    0.48
     VALUES
    0.46
    values
    0.44
     values
    0.43
    VALUES
    0.42
     outlier
    0.42
    値
    0.42
     outliers
    0.42
    VALUE
    0.41
    tol
    0.41
    Activations Density 0.007%

    No Known Activations