© 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. 73829
    Prev
    Next
    INDEX
    Explanations

    breathing

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

    This neuron detects content related to breathing, respiration, and breath control.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Boarding
    -0.79
    wendige
    -0.77
     transcrip
    -0.76
    PROLOG
    -0.75
     Saka
    -0.74
     METRO
    -0.73
    Pon
    -0.73
     Magna
    -0.71
    💊
    -0.70
     intangible
    -0.69
    POSITIVE LOGITS
     breathing
    2.08
     breathe
    1.69
     breath
    1.65
    breathing
    1.55
     Breathing
    1.55
     Breath
    1.51
    Breathing
    1.41
     respirar
    1.32
     Breathe
    1.24
     respiration
    1.23
    Activations Density 0.017%

    No Known Activations