© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128292
    Prev
    Next
    INDEX
    Explanations

    SQL FROM clauses

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

    The neuron fires on common SQL reserved keywords (e.g. SELECT, FROM, WHERE, JOIN, GROUP, ORDER, AND, AS).

    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
     incluindo
    -1.98
     ampio
    -1.94
     of
    -1.90
    ーズン
    -1.83
    扨
    -1.82
    怍
    -1.80
     purpoſe
    -1.77
    了
    -1.75
     quotidi
    -1.74
     tohoto
    -1.73
    POSITIVE LOGITS
    _
    2.94
    ”
    2.20
    ,”
    2.05
    ’
    1.99
     it
    1.95
    ‘
    1.94
     all
    1.93
     one
    1.91
     this
    1.89
     “
    1.84
    Activations Density 0.014%

    No Known Activations