© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82852
    Prev
    Next
    INDEX
    Explanations

    applications and workloads

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

    The neuron fires on domain-specific technical keywords describing system features or workloads (e.g. production, support, hosting, virtualization, database).

    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
    hardware
    -0.93
    硬件
    -0.83
     yöntem
    -0.81
    Oby
    -0.80
    ggings
    -0.79
    HARDWARE
    -0.79
     hardware
    -0.78
    +}$
    -0.77
    Gesam
    -0.75
     tqdm
    -0.75
    POSITIVE LOGITS
     workloads
    1.75
     applications
    1.59
     application
    1.30
    applications
    1.23
     workload
    1.23
    Applications
    1.20
     Apps
    1.16
     Applications
    1.16
     приложения
    1.15
    Apps
    1.14
    Activations Density 0.111%

    No Known Activations