© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25378
    Prev
    Next
    INDEX
    Explanations

    SQL CREATE TABLE statements

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

    This neuron activates on SQL DDL table‐definition syntax, particularly “CREATE TABLE …(” and the following column‐declaration structure.

    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
     should
    -1.55
     allerede
    -1.34
     our
    -1.30
    readFileSync
    -1.24
     it
    -1.24
     but
    -1.24
     three
    -1.21
     or
    -1.20
     that
    -1.17
     škole
    -1.16
    POSITIVE LOGITS
     Atención
    1.11
    ężczy
    1.11
     folgender
    1.05
    分かります
    1.03
     REALLY
    1.01
     vider
    1.00
     vastly
    0.99
    躋
    0.99
    ようで
    0.96
     '#'
    0.96
    Activations Density 0.032%

    No Known Activations