© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8266
    Prev
    Next
    INDEX
    Explanations

    QR code, barcode, sticker

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

    The neuron activates on mentions of machine‐readable codes and identifiers (e.g. Snapcodes, QR codes, barcodes, RFID tags).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical product descriptions and specifications, especially for RFID and technology companies.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of machine-readable identification and tracking technologies, especially digital codes, tags, and scanning systems.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Persians
    0.69
    பால
    0.66
     пане
    0.62
     prostaglandin
    0.61
    Ǻ
    0.60
     SOCK
    0.59
    ATIVA
    0.59
     PGE
    0.58
     feta
    0.58
     boul
    0.57
    POSITIVE LOGITS
     QR
    2.27
    QR
    2.05
     qr
    1.95
    二维码
    1.90
    qrcode
    1.86
    qr
    1.83
    QRCode
    1.81
     QRCode
    1.80
    Qr
    1.74
     barcode
    1.50
    Activations Density 0.128%

    No Known Activations