© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100769
    Prev
    Next
    INDEX
    Explanations

    CREATE TABLE statements

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

    the keyword "TABLE" in SQL CREATE TABLE statements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires whenever it sees the SQL keyword “TABLE.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    粢
    -1.72
    ímetros
    -1.56
    ISING
    -1.56
    ronesia
    -1.52
    yled
    -1.52
     faccio
    -1.50
    
    -1.49
    蟥
    -1.46
     dobbiamo
    -1.45
     โ
    -1.44
    POSITIVE LOGITS
     of
    1.86
    quelize
    1.38
    ”
    1.37
     inoltre
    1.34
    したり
    1.34
     légumes
    1.28
    ”、“
    1.27
     œufs
    1.27
    čku
    1.26
     pâtes
    1.25
    Activations Density 0.002%

    No Known Activations