© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60026
    Prev
    Next
    INDEX
    Explanations

    thymus and T cell development

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

    terminology and concepts related to T cells, thymus, and immune system functioning.

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

    This neuron specializes in picking out immunology jargon, especially terms related to T cells (e.g. “T cell,” “receptor,” “TCR,” “thymus,” “cytokine,” “transgenic,” etc.).

    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
    桂
    -0.81
    торт
    -0.79
    tungs
    -0.78
     trữ
    -0.73
     diam
    -0.71
    峒
    -0.71
    參見
    -0.71
    bben
    -0.69
    🏕
    -0.69
    FON
    -0.68
    POSITIVE LOGITS
     thym
    1.98
     thy
    1.66
    thym
    1.35
     thyme
    1.27
    thy
    1.23
     Thyme
    1.21
     Thy
    1.20
    Thy
    1.06
     TCR
    1.02
     lympho
    0.96
    Activations Density 0.176%

    No Known Activations