© 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. 33508
    Prev
    Next
    INDEX
    Explanations

    saving or saved

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

    The neuron strongly activates on language about reserving or allocating critical medical masks (e.g. “allowing critical medical masks to be reserved for health professionals”).

    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
    dames
    -0.78
     mosquito
    -0.77
    ucine
    -0.76
     Dieu
    -0.74
    柾
    -0.73
    phene
    -0.72
     mémoire
    -0.72
    Exped
    -0.71
     fija
    -0.70
    bindingNavigator
    -0.70
    POSITIVE LOGITS
     save
    5.09
     saved
    5.06
     saving
    4.91
    save
    4.66
    Save
    4.66
     Save
    4.38
     saves
    4.25
    saving
    4.06
    saved
    3.98
    Saving
    3.97
    Activations Density 0.037%

    No Known Activations