© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77528
    Prev
    Next
    INDEX
    Explanations

    species classification and geographic locations

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

    This neuron detects academic or scientific references, particularly author names and botanical/taxonomic citations in research 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
     бое
    -0.75
    小松
    -0.73
     méta
    -0.70
    するため
    -0.68
    鵲
    -0.67
     ту
    -0.66
    alimentation
    -0.66
     blacks
    -0.65
     بدان
    -0.64
    логу
    -0.63
    POSITIVE LOGITS
     Kew
    0.93
    Reveal
    0.85
     voucher
    0.83
     Reveal
    0.83
    USDA
    0.82
     botanist
    0.82
    УП
    0.79
    Missouri
    0.79
     Botany
    0.77
     Botanical
    0.77
    Activations Density 0.033%

    No Known Activations