© 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. 104331
    Prev
    Next
    INDEX
    Explanations

    IgG antibody subclasses

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

    mentions of antibodies, immunoglobulins (IgG, IgA, IgE), and immune-related proteins in scientific contexts.

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

    The neuron is primarily sensitive to numerical tokens and numeric expressions (e.g. counts, measurements) in the text.

    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
    g
    -1.87
    (
    -1.86
    er
    -1.74
     militer
    -1.61
    a
    -1.59
    al
    -1.58
     augusti
    -1.57
     ditt
    -1.55
    ing
    -1.55
    ia
    -1.51
    POSITIVE LOGITS
     uiteindelijk
    1.65
    鰱
    1.51
     Genau
    1.51
     follows
    1.44
     Entste
    1.41
     één
    1.40
     Historically
    1.39
     Möglich
    1.39
    byshev
    1.39
     “
    1.38
    Activations Density 0.102%

    No Known Activations