© 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. 90577
    Prev
    Next
    INDEX
    Explanations

    animal parts as descriptors

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

    taxonomic names and anatomical parts of animals and insects.

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

    This neuron detects Latin taxonomic names (genus and species epithets) in scientific species descriptions.

    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
    ↵↵
    -1.63
    u
    -1.45
     these
    -1.27
    (
    -1.23
    lion
    -1.20
     castig
    -1.20
     gesamten
    -1.19
     NUE
    -1.18
     meisten
    -1.16
    聲音
    -1.16
    POSITIVE LOGITS
    <>());
    1.85
    ("]");
    1.71
    IActionResult
    1.71
    ThemeOverlay
    1.65
    ViewInit
    1.59
    (")");
    1.55
    >());
    1.52
    ("")){
    1.50
    |$.
    1.50
    }=
    1.48
    Activations Density 0.093%

    No Known Activations