© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21119
    Prev
    Next
    INDEX
    Explanations

    tumor necrosis factor alpha and interleukins

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

    The neuron detects cytokines and interleukins in scientific medical text, particularly IL-6, IL-10, TNF, and other immune signaling molecules.

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

    This neuron identifies specific cytokine and related signaling protein names (e.g. interleukins, tumor necrosis factor, leukemia inhibitory factor, oncostatin M).

    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
    in
    -1.78
    f
    -1.70
    ᐕ
    -1.65
     who
    -1.59
    isActive
    -1.54
    NESSEE
    -1.52
    s
    -1.48
    ┍
    -1.48
    ,--
    -1.47
    。『
    -1.41
    POSITIVE LOGITS
     mogelijk
    1.52
    powiedz
    1.39
    vky
    1.38
    ₤
    1.38
    だそうです
    1.36
     yanlış
    1.36
    ekš
    1.34
    onomous
    1.34
     konuş
    1.33
     Encuentra
    1.31
    Activations Density 0.330%

    No Known Activations