© 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. 69976
    Prev
    Next
    INDEX
    Explanations

    computer code and electronics

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

    The neuron fires on technical “bus” terms—especially in industrial networking contexts like Fieldbus, Ethernet-based fieldbus protocols, gateways, and related data-transmission terminology.

    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
    searchResults
    -0.84
     convoy
    -0.75
    firmasi
    -0.74
    EFIAPI
    -0.72
    Cevapla
    -0.71
    }^{-}\
    -0.71
    рін
    -0.70
    pretation
    -0.70
    ynen
    -0.69
     Электро
    -0.69
    POSITIVE LOGITS
     CPU
    1.11
    CPU
    1.05
    Cpu
    0.96
    cpu
    0.94
     cpu
    0.87
     CPUs
    0.73
    MPI
    0.71
    processable
    0.70
    rů
    0.69
     forbin
    0.69
    Activations Density 0.013%

    No Known Activations