© 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. 34-GEMMASCOPE-RES-131K
    7. 75891
    Prev
    Next
    INDEX
    Explanations

    insert into values clause

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

    The neuron detects SQL code tokens—especially DML keywords (like INSERT, VALUES, SELECT) and associated table or column identifiers.

    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
     mouseY
    -0.83
    .(*
    -0.82
     зависимости
    -0.81
    guardo
    -0.81
    업
    -0.80
    漳
    -0.80
    лива
    -0.77
    WILLIAM
    -0.77
    .**
    -0.76
    ADC
    -0.74
    POSITIVE LOGITS
    ?,?,
    1.18
    ENCES
    0.87
    եկ
    0.80
    Fns
    0.79
    ?;
    0.78
    =:
    0.77
     Fim
    0.75
    最初から
    0.74
    気がします
    0.73
     Introduced
    0.73
    Activations Density 0.009%

    No Known Activations