© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3396
    Prev
    Next
    INDEX
    Explanations

    SQL window functions

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

    This neuron responds to mentions of SQL window (analytic) functions—especially running‐sum or similar OVER(...) constructs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     燈
    -0.76
    vettes
    -0.72
     Harmony
    -0.71
    skrä
    -0.71
     Aman
    -0.71
    tizado
    -0.70
     Glam
    -0.70
     bira
    -0.70
    每周
    -0.70
    zeption
    -0.69
    POSITIVE LOGITS
    ROW
    1.20
     ROW
    1.13
     row
    1.05
    partition
    1.02
    row
    1.01
     rank
    0.95
    ROWS
    0.95
    Window
    0.94
    Row
    0.94
    window
    0.94
    Activations Density 0.086%

    No Known Activations