© 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. 90597
    Prev
    Next
    INDEX
    Explanations

    receipts and following items

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

    The main thing this neuron does is detect mentions of the word “receipt.”

    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
     –
    -3.47
    os
    -2.81
    –
    -2.66
    m
    -2.63
    y
    -2.59
    ne
    -2.55
    <em>
    -2.55
     —
    -2.53
    of
    -2.50
    ،
    -2.44
    POSITIVE LOGITS
     preocupado
    2.66
     sellado
    2.56
    
    2.53
     interesado
    2.53
    齪
    2.52
     concentrado
    2.50
     fortalec
    2.48
     estabiliz
    2.45
     armado
    2.42
     protegido
    2.42
    Activations Density 0.001%

    No Known Activations