© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32116
    Prev
    Next
    INDEX
    Explanations

    sp sql procedures and related

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

    This neuron fires on SQL Server stored‐procedure identifiers (e.g. the “sp_…” procedure names and related SP/EXEC tokens).

    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
     well
    -0.89
     Cheese
    -0.77
     сливо
    -0.75
    från
    -0.75
     typing
    -0.74
     argued
    -0.73
     Product
    -0.72
    atikan
    -0.71
     ton
    -0.69
    ʐ
    -0.69
    POSITIVE LOGITS
     SP
    1.32
     SPC
    1.15
    SP
    1.02
     sp
    1.01
     SPM
    0.88
     SPH
    0.88
     СП
    0.86
     SPIN
    0.85
     SPO
    0.85
    sp
    0.83
    Activations Density 0.060%

    No Known Activations