© 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. 93919
    Prev
    Next
    INDEX
    Explanations

    column types and constraints

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

    This neuron detects the use of “Column” in XAML DataGrid (specifically DataGridTextColumn) definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical column or table names in database or UI code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to columns—especially column definitions, names, or headers in code and database contexts.

    oai_token-act-pair · gpt-5Triggered 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
    тів
    -0.83
     tomen
    -0.82
    OMON
    -0.80
     pinching
    -0.79
     './
    -0.79
     メニュー
    -0.79
     grego
    -0.78
    '/',
    -0.76
     DialogInterface
    -0.75
     Norr
    -0.75
    POSITIVE LOGITS
    ")]
    0.86
     can
    0.77
     incrementar
    0.73
    XCTAssertEqual
    0.71
     ন
    0.71
    藍
    0.70
    ]]=
    0.69
    JPanel
    0.69
     напо
    0.69
     not
    0.67
    Activations Density 0.001%

    No Known Activations