© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93549
    Prev
    Next
    INDEX
    Explanations

    enzyme-linked immunoassay

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

    technical terms in scientific or software contexts, particularly related to linking or connections in code and immunological assays.

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

    The neuron consistently fires on the word “linked” (as in “enzyme-linked”), i.e. it flags occurrences of “linked” in hyphenated technical 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_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
    abbé
    -0.70
    sells
    -0.67
    brian
    -0.67
     Brian
    -0.65
     Запад
    -0.64
     Social
    -0.64
     SG
    -0.63
    Brian
    -0.63
     Euro
    -0.63
     social
    -0.63
    POSITIVE LOGITS
     erw
    0.73
     nerves
    0.72
    blumen
    0.71
     CDF
    0.70
    нгредієнти
    0.69
    Publica
    0.68
    PERFORMANCE
    0.68
     Sarac
    0.68
    APR
    0.67
    ليب
    0.67
    Activations Density 0.075%

    No Known Activations