© 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. 70873
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT statements

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

    The neuron activates on SQL reserved words and syntax tokens (e.g. SELECT, COUNT, TO_CHAR, etc.).

    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
     Asegúrese
    -1.22
    aktu
    -1.11
     perder
    -1.07
    backen
    -1.06
    Entonces
    -1.06
    ‌.
    -1.01
    Mientras
    -1.01
    ingabe
    -1.00
     kabát
    -1.00
     mexicanos
    -0.98
    POSITIVE LOGITS
     from
    1.22
     to
    1.00
     upvotes
    0.98
    ,
    0.96
     finally
    0.96
     χωρίς
    0.92
     into
    0.91
    ล์
    0.90
    y
    0.87
     noce
    0.86
    Activations Density 0.029%

    No Known Activations