© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2739
    Prev
    Next
    INDEX
    Explanations

    database systems and SQL

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

    The neuron fires on technical references to database services—especially MySQL (errors, connectors, server access, queries, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RG
    0.57
    轨道
    0.55
     Coates
    0.54
    RG
    0.53
    scor
    0.53
    쑹
    0.52
     UG
    0.51
    ขน
    0.50
    isVideo
    0.50
    铑
    0.50
    POSITIVE LOGITS
     MySQL
    1.86
    MySQL
    1.85
     mysql
    1.76
    mysql
    1.70
     MYSQL
    1.69
     InnoDB
    1.67
    MYSQL
    1.59
    InnoDB
    1.52
    mysqli
    1.39
     mysqli
    1.37
    Activations Density 0.071%

    No Known Activations