© 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. 55926
    Prev
    Next
    INDEX
    Explanations

    trustee or LLC

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

    The neuron detects formal mentions of a trustee’s appointment in a legal document (e.g. “Trustee of the … Revocable Living Trust”).

    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
     in
    -1.06
    менный
    -0.87
     important
    -0.81
     [
    -0.77
    bust
    -0.74
     implementation
    -0.74
    Local
    -0.73
     בק
    -0.72
     unparalleled
    -0.72
     should
    -0.71
    POSITIVE LOGITS
     trustee
    1.17
     property
    1.17
     properties
    1.07
     ดี
    1.03
     Trustee
    0.98
     LLC
    0.98
     trustees
    0.95
     logements
    0.94
     eſt
    0.89
     motorcycles
    0.89
    Activations Density 0.021%

    No Known Activations