© 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. 20974
    Prev
    Next
    INDEX
    Explanations

    species delimitation

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

    taxonomy listings showing species classifications in biological articles.

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

    This neuron specializes in spotting mentions of the taxonomic rank “species.”

    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
    ༷
    -2.03
    zös
    -1.93
    歃
    -1.88
    ”;
    -1.80
     esque
    -1.77
    蚰
    -1.77
    ”-
    -1.73
    "=
    -1.68
    扨
    -1.63
    上の
    -1.62
    POSITIVE LOGITS
    2
    2.05
    냑
    2.03
    地说
    1.99
    哈哈哈哈
    1.75
     Veränderungen
    1.72
     festgestellt
    1.70
     บาง
    1.69
    鉀
    1.69
    빼
    1.67
    ابي
    1.66
    Activations Density 0.042%

    No Known Activations