© 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. 55676
    Prev
    Next
    INDEX
    Explanations

    physical activity and inactivity

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

    This neuron specifically detects mentions of physical activity (including the abbreviation “PA”) and its associated quantitative measures.

    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
    Nodes
    -0.77
    کارت
    -0.73
    ppings
    -0.73
     Terminal
    -0.71
    hol
    -0.69
    Paths
    -0.69
    hibition
    -0.67
     années
    -0.66
    toast
    -0.66
    athione
    -0.66
    POSITIVE LOGITS
     sedentary
    1.41
     inactive
    1.27
     accelerometer
    1.18
     inactivity
    1.13
     girls
    1.09
     Inactive
    1.09
    inactive
    1.06
     HEPA
    1.02
     kids
    1.01
     leisure
    0.98
    Activations Density 0.111%

    No Known Activations