© 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. 10-GEMMASCOPE-RES-131K
    7. 60969
    Prev
    Next
    INDEX
    Explanations

    neurotransmitters

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

    the term "neurotransmitters" in scientific or medical contexts.

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

    The neuron activates on occurrences of the term “neurotransmitters” (and its close variants), effectively identifying mentions of neurotransmitters in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    黑衣
    -2.03
    毟
    -1.95
    ＝＝＝＝
    -1.87
     inoxydable
    -1.85
    wouldn
    -1.84
     sinyal
    -1.83
    敉
    -1.82
    >';
    -1.81
    opies
    -1.80
     aksi
    -1.79
    POSITIVE LOGITS
    '
    2.22
    .
    1.90
    ↵↵
    1.90
     As
    1.77
     Now
    1.76
     Not
    1.73
     
    1.71
     A
    1.70
     It
    1.66
     And
    1.66
    Activations Density 0.015%

    No Known Activations