© 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. 22-GEMMASCOPE-RES-131K
    7. 39503
    Prev
    Next
    INDEX
    Explanations

    receptor subtypes

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

    scientific or medical terminology related to biological and chemical structures or processes.

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

    The neuron activates on JavaScript module-import patterns, especially the string paths inside require(...) calls.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    менять
    -0.92
    窖
    -0.82
    dans
    -0.82
    etal
    -0.81
    msgTypes
    -0.80
     姆
    -0.79
     prosz
    -0.78
     Wisata
    -0.77
    msgSender
    -0.77
    大師
    -0.77
    POSITIVE LOGITS
    Созда
    0.82
     sommige
    0.82
     теа
    0.77
    
    0.75
    Minha
    0.74
    Avan
    0.73
     ہیں۔
    0.73
     MUCH
    0.72
    zegovina
    0.71
    魎
    0.71
    Activations Density 0.081%

    No Known Activations