© 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. 127453
    Prev
    Next
    INDEX
    Explanations

    ryanodine receptor channels

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

    scientific terminology related to diseases, especially animal and infectious diseases like swine fever, botulinum, and Chagas disease.

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

    The neuron strongly responds to technical names of pathogens, microbes, or disease agents (e.g. Latin species names and virus/disease terms).

    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
     vlasy
    -1.50
    艽
    -1.44
    ⚋
    -1.42
    隴
    -1.41
    壟
    -1.41
    LAMP
    -1.41
    鹀
    -1.36
    🐭
    -1.35
    quées
    -1.34
     Règlement
    -1.34
    POSITIVE LOGITS
    </strong>
    1.73
    <em>
    1.43
    t
    1.41
     then
    1.37
    ти
    1.36
    not
    1.36
    b
    1.32
     more
    1.28
    1
    1.27
    만
    1.27
    Activations Density 0.134%

    No Known Activations