© 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. 90775
    Prev
    Next
    INDEX
    Explanations

    blood group antigens and typing

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

    blood group and biochemical terminology related to glycoproteins, antigens, and molecular structures.

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

    This neuron detects mentions of blood‐group terminology (e.g. blood group, antigen, Rh, Kell, blood type, typing, transfusion).

    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
    er
    -1.73
     bestanden
    -1.47
    ти
    -1.41
    
    -1.37
    col
    -1.34
    ing
    -1.34
    co
    -1.34
     factors
    -1.34
    he
    -1.33
    //
    -1.33
    POSITIVE LOGITS
     högre
    1.39
    蒞
    1.32
    dataflow
    1.31
     grandeur
    1.30
    bbq
    1.30
    nancy
    1.28
    zestaw
    1.28
    madonna
    1.25
    )=>{
    1.25
    éné
    1.24
    Activations Density 0.090%

    No Known Activations