© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108803
    Prev
    Next
    INDEX
    Explanations

    immune complexes

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

    molecular biology terms related to immune complexes and protein interactions.

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

    The neuron fires strongly on technical immunology terms—especially mentions of “immune complexes,” complement‐system activation, and related removal or circulation processes.

    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
    career
    -0.80
    Couple
    -0.73
    chapter
    -0.73
     Classified
    -0.72
    ⋂
    -0.71
    contr
    -0.71
    Subclass
    -0.70
    counter
    -0.69
    capital
    -0.68
    carry
    -0.68
    POSITIVE LOGITS
     complex
    4.22
     complexes
    3.80
    complex
    3.30
     Complex
    3.00
    COMPLEX
    2.88
    Complex
    2.83
     komplex
    2.78
     Complexes
    2.75
     complejo
    2.75
     комплек
    2.75
    Activations Density 0.176%

    No Known Activations