© 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. 10-GEMMASCOPE-RES-131K
    4. 105897
    Prev
    Next
    INDEX
    Explanations

    patent document

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

    The neuron specializes in spotting patent-document citations and identifiers (e.g. occurrences of “Patent,” “Pat.,” “No.,” and their associated document numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     are
    -3.42
     referrerpolicy
    -2.77
    itemBuilder
    -2.48
    苼
    -2.47
    ."
    -2.39
    ic
    -2.34
     endforeach
    -2.31
    al
    -2.30
     {
    
    
    -2.25
    
    -2.23
    POSITIVE LOGITS
    ↵
    3.95
    すでに
    3.16
     Fähig
    2.83
     üblichen
    2.73
     groundbreaking
    2.73
     Änder
    2.61
    戰爭
    2.55
     csomag
    2.50
    Being
    2.47
     gesuchten
    2.47
    Activations Density 0.029%

    No Known Activations