© 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. 90849
    Prev
    Next
    INDEX
    Explanations

    insect family names ending in idae

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

    descriptions of insects, particularly moths, focusing on their taxonomic classification and physical characteristics.

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

    This neuron detects taxonomic and scientific names (especially Latin genus, species, and family names) in descriptions of moths and other organisms.

    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
    這個
    -1.39
    prende
    -1.34
    gencias
    -1.29
    licante
    -1.26
     franz
    -1.22
    这个
    -1.22
    と話
    -1.18
    re
    -1.16
    ,..
    -1.14
     oa
    -1.14
    POSITIVE LOGITS
    andere
    1.47
    ків
    1.41
    XCTAssertEqual
    1.38
    textTheme
    1.34
    tać
    1.33
    }}^
    1.33
    kesan
    1.30
    왼
    1.28
     Sólo
    1.27
    BACA
    1.26
    Activations Density 0.093%

    No Known Activations