© 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. 10-GEMMASCOPE-RES-131K
    4. 99492
    Prev
    Next
    INDEX
    Explanations

    sql commands

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

    The neuron fires on SQL statement keywords (e.g. INSERT, INTO, SELECT, UPDATE, CREATE, 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_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
    謌
    -1.46
    朏
    -1.41
    
    -1.38
    ITERATURE
    -1.37
    Wrestling
    -1.33
    ⚥
    -1.31
     และ
    -1.31
    Zacks
    -1.30
    amerikanische
    -1.29
    Sentiment
    -1.28
    POSITIVE LOGITS
    _
    1.73
     instead
    1.68
    ->
    1.57
     \
    1.55
     only
    1.55
     !=
    1.50
     some
    1.48
    ('
    1.48
    ='
    1.42
    ::
    1.41
    Activations Density 0.064%

    No Known Activations