© 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. 10-GEMMASCOPE-RES-131K
    7. 21473
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT statements

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

    The neuron activates on instances of the SQL keyword “SELECT” (i.e. SELECT query clauses).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    SQL data-retrieval statements in code snippets, particularly database query clauses.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the SQL keyword "SELECT" in database queries.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    r
    -2.78
    i
    -2.48
    //
    -2.45
    f
    -2.23
    !"
    -2.23
     was
    -2.23
    d
    -2.22
    K
    -2.19
    !!
    -2.19
     با
    -2.17
    POSITIVE LOGITS
    艄
    2.75
    怎样的
    2.39
    mpagne
    2.36
     perfecte
    2.23
    鷙
    2.22
    ing
    2.19
    歘
    2.19
    饜
    2.17
     basili
    2.16
    美国的
    2.16
    Activations Density 0.007%

    No Known Activations