© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9343
    Prev
    Next
    INDEX
    Explanations

    serial communication devices

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

    The neuron fires on mentions of technical hardware components, interfaces, and communication protocols (e.g. UART, RS-232, terminals, boards, DPA modules).

    oai_token-act-pair · o4-miniTriggered 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
    🕌
    0.58
     Steering
    0.56
    TaskId
    0.53
    raltar
    0.52
    ektir
    0.50
     ترکیه
    0.50
    ฎ
    0.50
    aikum
    0.50
    日本製
    0.49
    鉭
    0.49
    POSITIVE LOGITS
     serial
    1.43
     Serial
    1.41
    Serial
    1.36
    serial
    1.34
     SERIAL
    1.27
    baud
    1.20
    SERIAL
    1.19
    串口
    1.16
     सीरियल
    1.05
     UART
    1.01
    Activations Density 0.108%

    No Known Activations