© 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. 34-GEMMASCOPE-RES-131K
    7. 57062
    Prev
    Next
    INDEX
    Explanations

    SQL prepare statements

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

    The neuron fires on mentions of “Prepared Statement” (and its variants like prepareStatement) in code or text.

    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
    isit
    -0.77
    izin
    -0.75
     mõ
    -0.74
    setModel
    -0.74
    ียว
    -0.73
    дово
    -0.73
    iane
    -0.73
    crisy
    -0.72
     contato
    -0.71
     serviço
    -0.70
    POSITIVE LOGITS
     prepared
    1.28
     Prepared
    1.22
    Prepared
    1.13
    prepared
    1.09
     Callable
    0.94
    预
    0.93
     preparados
    0.92
     přip
    0.88
     prepar
    0.87
     preparazione
    0.87
    Activations Density 0.007%

    No Known Activations