© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103164
    Prev
    Next
    INDEX
    Explanations

    SQL table operations

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

    the word "TABLE" in technical or structured data contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on appearances of the literal token “TABLE,” i.e. references to tables in the text.

    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
     wth
    -3.30
     '
    -2.56
     be
    -2.52
        
    -2.33
    未能
    -2.31
    ’
    -2.31
     avec
    -2.23
     tomando
    -2.16
     intrepid
    -2.14
     ‘
    -2.13
    POSITIVE LOGITS
    e
    2.95
    there
    2.91
    0
    2.81
    
    2.73
     bière
    2.73
    TABLE
    2.64
     désol
    2.56
     magasiner
    2.50
     regler
    2.48
    しなければ
    2.48
    Activations Density 0.003%

    No Known Activations