© 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. 83240
    Prev
    Next
    INDEX
    Explanations

    physical activity recommendations and durations

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

    The neuron fires on mentions of physical activity intensity levels—especially phrases contrasting sedentary behavior with moderate‐to‐vigorous physical activity (e.g. “Moderate‐to‐Vigorous Physical Activity,” “MVPA,” “sedentary behavior”).

    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
    ửi
    -0.83
     yeme
    -0.80
     impress
    -0.78
    nyv
    -0.77
    >(&
    -0.77
     apartments
    -0.76
    oraf
    -0.76
     Besonder
    -0.75
    hamos
    -0.74
     '('
    -0.73
    POSITIVE LOGITS
     minutes
    1.30
     weekly
    1.09
     moderate
    1.05
     adults
    1.02
     mē
    0.96
     recommended
    0.94
     Moderate
    0.90
     recommendation
    0.90
    每周
    0.89
    Intensity
    0.88
    Activations Density 0.026%

    No Known Activations