© 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. 27961
    Prev
    Next
    INDEX
    Explanations

    database table creation

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

    This neuron detects SQL “CREATE TABLE” statements (especially the keywords in a CREATE TABLE definition).

    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
    preprint
    -1.02
    typically
    -1.02
     Trotzdem
    -1.01
    biendo
    -0.97
     semelh
    -0.96
    vaila
    -0.96
     legendar
    -0.95
     conforto
    -0.95
    常常
    -0.94
    interprétation
    -0.94
    POSITIVE LOGITS
     in
    1.34
     creating
    1.30
     создавать
    1.23
    创建
    1.23
    творення
    1.20
     establishing
    1.18
     without
    1.16
     create
    1.14
     Creating
    1.14
     new
    1.11
    Activations Density 0.037%

    No Known Activations