© 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. 10-GEMMASCOPE-RES-131K
    7. 72921
    Prev
    Next
    INDEX
    Explanations

    logical AND operator conditions

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

    The neuron is strongly activated by major SQL clause keywords (especially AND, ON, JOIN) in uppercase.

    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
     constater
    -1.95
    镡
    -1.88
    なども
    -1.84
     hormigón
    -1.77
     siè
    -1.77
    ’，
    -1.73
    姽
    -1.71
     rése
    -1.71
    Türk
    -1.70
     MOORE
    -1.70
    POSITIVE LOGITS
    That
    2.73
     that
    2.52
    There
    2.34
    When
    2.22
     at
    2.20
     or
    2.17
     in
    2.16
     you
    2.09
    This
    2.09
     When
    2.05
    Activations Density 0.011%

    No Known Activations