© 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. 98850
    Prev
    Next
    INDEX
    Explanations

    document, order, invoice, date, source

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

    The neuron fires strongly on programming identifiers and technical tokens (e.g. class, package, import, or XML‐related names) in code snippets.

    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
     product
    -1.00
     price
    -0.94
     Product
    -0.86
     Produkt
    -0.84
    product
    -0.78
    Product
    -0.75
    脩
    -0.75
     assigned
    -0.74
     products
    -0.74
    ProductName
    -0.74
    POSITIVE LOGITS
     document
    1.56
    document
    1.52
    Document
    1.44
     dokument
    1.41
     documents
    1.41
     Document
    1.39
    documents
    1.34
     documento
    1.33
     Documents
    1.27
     doc
    1.27
    Activations Density 0.010%

    No Known Activations