© 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. 68843
    Prev
    Next
    INDEX
    Explanations

    glutamate and DA receptors

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

    This neuron activates for neurotransmitters and related terms in scientific contexts, particularly glutamate, NMDA, AMPA, GABA and their receptor systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    V
    -2.06
    D
    -1.93
    J
    -1.78
    过程中
    -1.76
    S
    -1.66
     have
    -1.65
    M
    -1.65
     These
    -1.64
     while
    -1.64
    K
    -1.62
    POSITIVE LOGITS
     Danke
    1.57
    かった
    1.49
    纠结
    1.48
     TALL
    1.48
    动了
    1.45
    >
    1.42
     Vielen
    1.42
     bienvenue
    1.41
    来了
    1.38
    來了
    1.38
    Activations Density 0.056%

    No Known Activations