© 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. 82626
    Prev
    Next
    INDEX
    Explanations

    maneuver and related movement

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

    The neuron detects technical terms and measurements related to pulmonary function testing (e.g., expiratory maneuvers, spirometry metrics).

    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
     учё
    -0.88
     Cinéma
    -0.76
    bó
    -0.73
    retched
    -0.71
    讯
    -0.71
     Modific
    -0.71
    Magnetic
    -0.70
    歯
    -0.70
    océ
    -0.70
     elektrik
    -0.70
    POSITIVE LOGITS
     maneuver
    3.36
     maneuvers
    2.95
     Mane
    2.78
     manoeuvre
    2.72
     manio
    2.53
     mano
    2.45
     manoeu
    2.42
     Mano
    2.41
    Mane
    2.41
     maneuvering
    2.30
    Activations Density 0.060%

    No Known Activations