© 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. 70017
    Prev
    Next
    INDEX
    Explanations

    property boundaries and sales

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

    This neuron detects formal legal document markers indicating party roles and representation (e.g., “for respondent,” “appellant,” “appellee,” or boilerplate introductions like “This is an…”).

    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
    atique
    -0.93
    受伤
    -0.87
    ourcing
    -0.84
    Katso
    -0.81
     siè
    -0.78
     szár
    -0.77
    izz
    -0.76
    paul
    -0.75
     kín
    -0.75
    uka
    -0.75
    POSITIVE LOGITS
     boundary
    1.59
    boundary
    1.35
     boundaries
    1.33
     seller
    1.26
     sellers
    1.19
    Boundary
    1.17
     encroach
    1.15
     zoning
    1.09
    境界
    1.05
     Boundary
    1.03
    Activations Density 0.022%

    No Known Activations