© 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. 10-GEMMASCOPE-RES-131K
    4. 123472
    Prev
    Next
    INDEX
    Explanations

    lymph nodes, vessels, organs

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

    anatomical terms related to the lymphatic system, particularly "lymph nodes" and lymphatic structures.

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

    This neuron specializes in detecting mentions of “lymph” and related terms referring to lymphatic structures (e.g. lymph nodes, lymphatic vessels).

    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
    </strong>
    -1.97
    ";
    -1.93
    7
    -1.88
    );
    -1.83
    $
    -1.81
    9
    -1.80
    6
    -1.80
    on
    -1.77
    ()
    -1.77
    8
    -1.77
    POSITIVE LOGITS
    geſ
    2.22
    戬
    2.16
     hauptsächlich
    2.16
    ܞ
    2.09
    犼
    2.06
    quot
    2.05
    𐬹
    2.05
    ⬈
    2.02
    𝓑
    1.99
    </h5>
    1.97
    Activations Density 0.038%

    No Known Activations