© 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. 58959
    Prev
    Next
    INDEX
    Explanations

    rx tx serial data

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

    The neuron fires on mentions of serial‐I/O or UART‐style hardware communication (e.g. “Serial,” “Port,” “tty,” “UART”) in code or discussion.

    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
    ronom
    -0.79
    mName
    -0.78
     üzerinde
    -0.75
     miejs
    -0.75
     disbursements
    -0.73
    Ʒ
    -0.73
     слоя
    -0.71
    ům
    -0.71
    ticelli
    -0.70
    FILM
    -0.70
    POSITIVE LOGITS
    rx
    1.26
    tx
    1.16
     transmission
    1.13
     RX
    1.12
    Tx
    1.11
     Rx
    1.09
    Rx
    1.07
    RX
    1.06
     data
    1.05
     rx
    1.05
    Activations Density 0.020%

    No Known Activations