© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19415
    Prev
    Next
    INDEX
    Explanations

    insert into and delete from

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

    This neuron detects SQL data-modification statements, especially “DELETE FROM” and “INSERT INTO.”

    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
    瑒
    -1.83
     lâmpada
    -1.65
     моя
    -1.65
    笵
    -1.62
    揸
    -1.59
    皤
    -1.58
     blancs
    -1.55
    𖤍
    -1.54
     sagesse
    -1.53
    鮃
    -1.53
    POSITIVE LOGITS
     and
    2.44
     pudieron
    1.57
     With
    1.56
     with
    1.55
     These
    1.54
     from
    1.51
     It
    1.49
     while
    1.46
     as
    1.45
     However
    1.44
    Activations Density 0.003%

    No Known Activations