© 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. 10-GEMMASCOPE-RES-131K
    7. 41543
    Prev
    Next
    INDEX
    Explanations

    sql inserts

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

    The neuron fires on SQL data‐manipulation keywords—especially the “INSERT” statements.

    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
    
    -2.38
    ⎔
    -2.30
     retirer
    -2.22
     fourni
    -2.20
     laisser
    -2.17
     glisser
    -2.16
    螣
    -2.16
    皷
    -2.14
    𓁹
    -2.11
     saudável
    -2.08
    POSITIVE LOGITS
     of
    4.44
     in
    2.45
     on
    2.39
     or
    2.36
    !!!
    2.05
    !!
    2.00
     and
    1.98
    !!!!
    1.98
    e
    1.91
     during
    1.89
    Activations Density 0.008%

    No Known Activations