© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75443
    Prev
    Next
    INDEX
    Explanations

    SQL ENGINE

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

    The neuron activates on SQL reserved keywords (especially DDL statements) such as CREATE, TABLE, IF, ROW, FORMAT, 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_34/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
     lisa
    -0.80
    Killed
    -0.74
     contamos
    -0.73
     Hôtel
    -0.73
     ơi
    -0.70
     zeigen
    -0.69
    Taxonomy
    -0.68
     Banjo
    -0.68
     Legisl
    -0.67
     Kei
    -0.66
    POSITIVE LOGITS
     ENGINE
    0.85
     COMMISSION
    0.80
    PCT
    0.74
    İZ
    0.74
     comment
    0.74
     volatility
    0.74
     Engine
    0.72
    gher
    0.71
     protests
    0.71
     engine
    0.71
    Activations Density 0.056%

    No Known Activations