© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29904
    Prev
    Next
    INDEX
    Explanations

    scan barcodes or QR codes

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

    The neuron is highly responsive to references to scanning or code‐reading technology (e.g. “scan,” “scanner,” “barcode,” “QR,” “reader,” “zxing,” “RFID,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Abraham
    -0.75
    靓
    -0.75
     Electoral
    -0.73
    érales
    -0.71
    estival
    -0.70
    paging
    -0.70
     forum
    -0.68
    vains
    -0.66
    🎪
    -0.66
    lucene
    -0.66
    POSITIVE LOGITS
     scan
    6.13
     scanning
    5.56
     scanned
    5.44
    scan
    5.41
     scans
    5.25
    Scan
    5.22
     Scan
    5.00
     Scanning
    4.50
     scanner
    4.50
    扫描
    4.47
    Activations Density 0.054%

    No Known Activations