© 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. 34-GEMMASCOPE-RES-131K
    7. 90445
    Prev
    Next
    INDEX
    Explanations

    taxonomic classification and species identification

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

    This neuron detects scholarly and scientific content, particularly recognizing dates, citations, and academic terminology in scientific papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Nasıl
    -1.02
    作战
    -1.02
     Bakterien
    -1.01
    ଵ
    -0.98
    门店
    -0.98
     Ancak
    -0.98
    անում
    -0.97
     Women
    -0.94
     Transcript
    -0.94
     Mechanism
    -0.93
    POSITIVE LOGITS
    Tax
    1.35
     taxa
    1.31
     taxonomic
    1.27
     taxon
    1.20
     voucher
    1.19
    Linnaeus
    1.05
    tax
    1.02
     curator
    1.01
    TAX
    1.00
    ismatic
    1.00
    Activations Density 0.067%

    No Known Activations