© 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. 83649
    Prev
    Next
    INDEX
    Explanations

    medical masks

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

    references to masks, particularly face masks worn for health or protection.

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

    The neuron strongly activates on mentions of masks—especially cloth or DIY face masks—and related instructions or usages (e.g., “face mask,” “cloth face mask,” “wear a mask”).

    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
    naked
    -0.79
    轉
    -0.72
    itability
    -0.70
     Wä
    -0.70
    Skin
    -0.69
    Beta
    -0.69
    Mg
    -0.69
     dependencies
    -0.68
    bankan
    -0.68
    Memory
    -0.67
    POSITIVE LOGITS
     masks
    2.47
     mask
    2.31
     Mask
    1.76
     Masks
    1.69
    mask
    1.67
    masks
    1.66
     surgical
    1.59
    Mask
    1.53
    Masks
    1.52
    マスク
    1.51
    Activations Density 0.008%

    No Known Activations