© 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. 22-GEMMASCOPE-RES-131K
    7. 36362
    Prev
    Next
    INDEX
    Explanations

    species names in scientific texts

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

    This neuron detects scientific taxonomic names, particularly species names in Latin with associated author citations.

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

    The neuron fires on the capitalized author or authority abbreviations that follow scientific Latin names (e.g. “L.”, “Duch.”, “Zimmerman”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     livelli
    -1.23
     riserv
    -1.20
     istnieje
    -1.12
     attivo
    -1.12
    来週
    -1.11
     nearby
    -1.09
    ことも
    -1.09
     novità
    -1.08
     invece
    -1.07
    になったら
    -1.07
    POSITIVE LOGITS
    macht
    1.09
    々な
    1.05
    Pilih
    1.02
    arschijnlijk
    1.02
    
    1.02
    古屋
    0.99
     histori
    0.99
    餃子
    0.98
     (
    0.97
    但是在
    0.96
    Activations Density 0.040%

    No Known Activations