© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60416
    Prev
    Next
    INDEX
    Explanations

    SQL WHERE clauses

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

    The main thing this neuron does is detect SQL DML and clause keywords (e.g. SELECT, DELETE, FROM, WHERE, AS).

    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
    </h2>
    -2.80
    '
    -2.77
     ‘
    -2.58
     weirdly
    -2.47
     out
    -2.41
     will
    -2.38
     in
    -2.36
     or
    -2.34
    !!!!
    -2.33
     after
    -2.31
    POSITIVE LOGITS
    犼
    3.02
    颪
    2.95
    蹰
    2.61
    茈
    2.59
     quintessential
    2.47
     raiſ
    2.47
    筇
    2.47
     viſ
    2.45
    妧
    2.41
    姽
    2.39
    Activations Density 0.047%

    No Known Activations