© 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. 22-GEMMASCOPE-RES-131K
    7. 28175
    Prev
    Next
    INDEX
    Explanations

    mysql commands and queries

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

    The neuron fires on occurrences of the token “mysql” (or “MySQL”), i.e. references to MySQL in queries or code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     But
    -2.48
     is
    -2.47
    ’
    -2.38
     we
    -2.34
    ,"
    -2.33
     was
    -2.31
     Also
    -2.22
    ).
    -2.20
     isn
    -2.17
     called
    -2.16
    POSITIVE LOGITS
    秾
    2.58
     チラ
    2.52
    抬手
    2.28
    .
    2.28
    The
    2.19
     fermer
    2.14
    鉭
    2.11
     撮っ
    2.08
    压制
    2.08
     буты
    2.06
    Activations Density 0.009%

    No Known Activations