© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 23541
    Prev
    Next
    INDEX
    Explanations

    SQL variable assignment and statements

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

    The neuron strongly activates on SQL code tokens (e.g. keywords, identifiers, symbols, numeric literals) rather than ordinary prose.

    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
    𝘠
    -0.90
     if
    -0.77
     should
    -0.75
    khó
    -0.75
    Mysql
    -0.75
    Soccer
    -0.72
    ácidos
    -0.71
     soccer
    -0.70
     rewarding
    -0.70
     جا
    -0.70
    POSITIVE LOGITS
     dbo
    1.03
    dbo
    0.88
    isnull
    0.82
    CONVERT
    0.79
     [
    0.79
    weck
    0.76
    Convert
    0.75
    ].[
    0.75
     Conversion
    0.75
     egenskaper
    0.73
    Activations Density 0.126%

    No Known Activations