© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87409
    Prev
    Next
    INDEX
    Explanations

    Tuberculosis (TB)

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

    references to tuberculosis, TB, and related medical terminology.

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

    The neuron responds to mentions of the disease “tuberculosis” (including its abbreviation “TB”) and related terms.

    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
    〤
    -2.78
    〠
    -2.53
    AdvEx
    -2.45
    鸸
    -2.27
    了啊
    -2.27
     叫
    -2.20
    </sup>
    -2.16
     喜欢
    -2.14
    ,
    -2.14
     ſhe
    -2.13
    POSITIVE LOGITS
    this
    2.69
    .”
    2.67
     dichas
    2.30
     nuestras
    2.25
    にい
    2.23
     the
    2.22
    k
    2.20
     This
    2.19
     habiendo
    2.17
    section
    2.13
    Activations Density 0.009%

    No Known Activations