© 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. 34-GEMMASCOPE-RES-131K
    7. 103306
    Prev
    Next
    INDEX
    Explanations

    legal tests and criteria

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

    The neuron activates on document section headings, titles, and other major legal‐style headings.

    oai_token-act-pair · o4-miniTriggered 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
    lers
    -0.81
    tao
    -0.78
     Veg
    -0.77
    etary
    -0.76
    melten
    -0.75
     pho
    -0.74
    щика
    -0.73
     الشعب
    -0.73
     вечером
    -0.72
    アノ
    -0.72
    POSITIVE LOGITS
     test
    2.55
     tests
    2.30
     criteria
    1.87
    test
    1.66
     Tests
    1.65
     analysis
    1.56
     testing
    1.50
    测试
    1.48
    tests
    1.46
     тест
    1.42
    Activations Density 0.024%

    No Known Activations