© 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. 25773
    Prev
    Next
    INDEX
    Explanations

    invoice #

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

    The neuron fires on multi‐character tokens that look like code identifiers or resource names—e.g. file paths, template/variable names, or UI objects like “order_forms,” “standard_cart,” “invoice,” etc.

    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
     welfare
    -0.77
    anode
    -0.74
     Medal
    -0.73
     أف
    -0.73
     posters
    -0.72
    élie
    -0.72
     poster
    -0.71
    nemo
    -0.71
     vibes
    -0.70
     census
    -0.69
    POSITIVE LOGITS
     invoice
    2.02
     invoices
    1.64
     Invo
    1.63
     invo
    1.61
    Invoice
    1.60
     Invoice
    1.59
    invoice
    1.48
    invo
    1.27
    Invo
    1.23
     bill
    1.12
    Activations Density 0.015%

    No Known Activations