© 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. 19086
    Prev
    Next
    INDEX
    Explanations

    court clerk working

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

    The neuron detects references to the court’s Clerk section or “Clerk” headings in legal 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_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
     witty
    -2.58
     immeasurable
    -2.53
     immense
    -2.41
     replete
    -2.38
    </b>
    -2.34
     momentous
    -2.28
     weary
    -2.27
     engender
    -2.25
     he
    -2.23
     hardcore
    -2.23
    POSITIVE LOGITS
     車場
    2.77
     είναι
    2.70
    鄚
    2.47
    geſ
    2.45
    
    2.38
     melaporkan
    2.34
     mengumumkan
    2.30
     MEXICO
    2.27
    We
    2.22
    If
    2.22
    Activations Density 0.003%

    No Known Activations