© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77270
    Prev
    Next
    INDEX
    Explanations

    serial and bus interfaces

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

    This neuron responds to mentions of hardware communication protocols or bus interfaces (e.g. RS-232/485, I²C, USB).

    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
     measurable
    -0.68
    uktur
    -0.66
    ฏ
    -0.66
     Yag
    -0.66
     nasty
    -0.65
    癥
    -0.65
    驻
    -0.65
     شام
    -0.65
     alqu
    -0.64
     watts
    -0.63
    POSITIVE LOGITS
     interface
    1.55
     buses
    1.48
     bus
    1.48
     serial
    1.41
     интерфей
    1.37
     interfaces
    1.29
     Interface
    1.25
    interface
    1.23
     interfaz
    1.21
     SPI
    1.20
    Activations Density 0.097%

    No Known Activations