© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10678
    Prev
    Next
    INDEX
    Explanations

    biological classification genus

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

    taxonomic terms related to biological classification, particularly the word "genus" and its associated hierarchy.

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

    The neuron specializes in spotting taxobox classification lines by detecting the taxonomic‐rank labels (like phylum, order, family, genus, species) in an article’s infobox.

    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
    扨
    -1.88
    齜
    -1.82
    槼
    -1.79
    笮
    -1.79
    TintMode
    -1.78
    搋
    -1.73
    鱘
    -1.73
    嫌弃
    -1.73
    rosophila
    -1.73
    ACIÓN
    -1.69
    POSITIVE LOGITS
    </h2>
    1.73
     is
    1.70
     of
    1.59
     \
    1.58
    :
    1.55
     —
    1.48
     kvä
    1.45
    ↵
    1.44
     充電
    1.41
    </sup>
    1.39
    Activations Density 0.018%

    No Known Activations