© 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. 32988
    Prev
    Next
    INDEX
    Explanations

    remedy technique, Outcome Measurement

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

    references to medicinal substances, treatments, and remedies.

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

    The neuron activates on mentions of substances or remedies—chemical, medicinal, or herbal (e.g. drink names, tinctures, infusions, “medicine,” “energy,” “absinthe”).

    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
     もう
    -0.81
     />';
    -0.70
     queens
    -0.70
     resmi
    -0.69
    Categorias
    -0.68
     Krypto
    -0.68
     proverbial
    -0.68
     intense
    -0.67
    Время
    -0.67
    tugas
    -0.67
    POSITIVE LOGITS
     sugar
    1.03
     granules
    0.90
     pellets
    0.88
     glob
    0.86
    lastonbury
    0.81
     Dyna
    0.79
     quantization
    0.76
     pellet
    0.76
     Sugar
    0.75
    sugar
    0.74
    Activations Density 0.009%

    No Known Activations