© 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. 22-GEMMASCOPE-RES-131K
    7. 67601
    Prev
    Next
    INDEX
    Explanations

    Related Art descriptions

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

    The neuron detects tokens that are part of formal section headings (e.g. “Field of the Invention,” “Description of the Related Art,” “Technical Field,” etc.) in patent documents.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     continue
    -1.04
     restent
    -0.91
    ---|---|
    -0.91
     specifik
    -0.90
    GroupLayout
    -0.90
    brahim
    -0.90
     могли
    -0.88
    wareness
    -0.87
    azzjoni
    -0.86
     muze
    -0.86
    POSITIVE LOGITS
     copious
    1.13
     collaborating
    1.05
    Organisator
    0.98
    prilis
    0.97
    gió
    0.95
    Indent
    0.93
    iguar
    0.91
     preceding
    0.91
     nutritious
    0.89
    omnie
    0.89
    Activations Density 0.067%

    No Known Activations