© 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. 59132
    Prev
    Next
    INDEX
    Explanations

    erythematous

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

    medical terms related to skin conditions, particularly redness and inflammation.

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

    The neuron fires on medical terms for redness or inflammation (e.g. “pink eye,” “conjunctivitis,” “erythema/erythro-” words, “redness,” 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_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
    Don
    -1.40
    .”
    -1.34
    </h4>
    -1.34
    loyed
    -1.33
    Please
    -1.32
    <h3>
    -1.31
        
    -1.30
    ”
    -1.29
    ```
    -1.25
    Ｉ
    -1.23
    POSITIVE LOGITS
     kırmızı
    1.48
     červen
    1.48
    Wady
    1.44
     red
    1.42
     professores
    1.41
     unaweza
    1.38
    plastik
    1.37
     síntesis
    1.35
    Berna
    1.34
    Neder
    1.33
    Activations Density 0.052%

    No Known Activations