© 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. 77001
    Prev
    Next
    INDEX
    Explanations

    IgG subclasses

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

    immunoglobulin references, particularly IgG and IgA antibody types and subclasses.

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

    The neuron strongly activates on mentions of antibody isotypes—especially immunoglobulin G (IgG) and its subclasses (e.g. IgG1, IgG2, IgG3, IgG4).

    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
    盤
    -0.85
    ้อมูล
    -0.77
    cinha
    -0.75
     matlab
    -0.73
    앵
    -0.73
     Generates
    -0.72
     scoops
    -0.72
     exorbit
    -0.71
     migrations
    -0.71
    姫
    -0.70
    POSITIVE LOGITS
     IgG
    1.70
     subclass
    1.40
    IgG
    1.36
     Fc
    1.30
     Ig
    1.17
     immunoglobulin
    1.16
    Ig
    1.11
    Fc
    1.09
     ig
    1.09
    otype
    1.07
    Activations Density 0.179%

    No Known Activations