© 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. 20350
    Prev
    Next
    INDEX
    Explanations

    graft-versus-host disease

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

    medical terminology related to graft-versus-host disease and transplantation.

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

    The neuron detects mentions of graft-versus-host (and related graft-versus-X) immunological contexts.

    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
     and
    -1.55
    tividade
    -1.42
     or
    -1.35
     organi
    -1.23
    начала
    -1.22
     suport
    -1.22
    📞
    -1.21
    </u>
    -1.20
     with
    -1.16
     experim
    -1.16
    POSITIVE LOGITS
    籥
    1.68
    ݯ
    1.55
     Ensuring
    1.54
     Schwierigkeiten
    1.48
    觧
    1.47
     conteúdo
    1.46
     dozen
    1.45
    Климат
    1.42
    喾
    1.42
     próprio
    1.41
    Activations Density 0.019%

    No Known Activations