© 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. 84557
    Prev
    Next
    INDEX
    Explanations

    CREATE TABLE

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

    The neuron detects SQL Data Definition Language keywords (e.g. CREATE, TABLE, IF, NOT, PRIMARY).

    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
    蛱
    -1.65
    Ꮀ
    -1.47
    鮰
    -1.43
    蟥
    -1.42
     its
    -1.42
    亗
    -1.34
    ſſen
    -1.34
    eronau
    -1.31
    वं
    -1.30
    鸲
    -1.29
    POSITIVE LOGITS
    It
    1.45
    Since
    1.45
    With
    1.43
    From
    1.42
     If
    1.38
    For
    1.35
    If
    1.34
    There
    1.32
     if
    1.27
     now
    1.27
    Activations Density 0.013%

    No Known Activations