© 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. 107465
    Prev
    Next
    INDEX
    Explanations

    lung

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

    references to respiratory system components like lungs, airways, and breathing.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects terms related to breathing and lung airflow (e.g. air, lung, inflation, airway, breath).

    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
     drip
    -0.81
    食べたい
    -0.79
    ❱
    -0.77
    语气
    -0.76
     выпла
    -0.75
    ocat
    -0.75
    Drip
    -0.71
     Drip
    -0.71
    predic
    -0.70
     comforts
    -0.70
    POSITIVE LOGITS
     lungs
    3.70
     lung
    2.92
    lungs
    2.56
    肺
    2.41
     Lung
    2.30
    Lung
    2.09
     pulmonary
    2.06
    lung
    1.93
    pulmonary
    1.68
     Pulmonary
    1.56
    Activations Density 0.044%

    No Known Activations