© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111640
    Prev
    Next
    INDEX
    Explanations

    CD T helper cells

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

    T cell types and immune cell markers in scientific/medical text about immunology.

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

    The neuron fires on immunology shorthand for specific T-lymphocyte subsets, i.e. CD-marker designations like “CD4+” or “CD8+” T cells.

    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
    ate
    -1.43
     хотел
    -1.36
    yte
    -1.26
    側は
    -1.24
     pauv
    -1.22
    を使う
    -1.19
     kebaya
    -1.17
     barnet
    -1.17
    CONTR
    -1.16
     presi
    -1.16
    POSITIVE LOGITS
    ࿚
    1.55
    Să
    1.41
     princesas
    1.38
    巍
    1.29
    toDouble
    1.28
    Género
    1.25
    calciatore
    1.25
    توضیحات
    1.25
     wyposaż
    1.24
     at
    1.23
    Activations Density 0.229%

    No Known Activations