© 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. 22-GEMMASCOPE-RES-131K
    7. 84171
    Prev
    Next
    INDEX
    Explanations

    CREATE TABLE statements with id columns

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

    This neuron activates on SQL CREATE TABLE statements, especially the backtick- or quote-delimited table and column identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     both
    -1.73
     både
    -1.31
    both
    -1.24
     sowohl
    -1.24
     Both
    -1.24
    Both
    -1.19
     kedua
    -1.16
     even
    -1.07
     zarówno
    -1.05
     ambos
    -1.05
    POSITIVE LOGITS
    OLVED
    0.92
    ocry
    0.91
    róleo
    0.90
    utura
    0.89
    Escola
    0.88
     symboles
    0.86
     pořád
    0.85
    チョイス
    0.85
     keo
    0.85
    Klo
    0.85
    Activations Density 0.002%

    No Known Activations