© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128084
    Prev
    Next
    INDEX
    Explanations

    This neuron identifies the numeric year (and related citation numbers) appearing in parentheses as part of a species’ taxonomic authority.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    species names and years

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

    taxonomic citations in scientific literature with author names and years.

    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_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
     damen
    -1.03
     yaris
    -1.01
     ;
    -0.99
    是怎么回事
    -0.97
    []]
    -0.97
    ］
    -0.97
     cabrio
    -0.96
     guangdong
    -0.94
     uchiha
    -0.94
     fatis
    -0.94
    POSITIVE LOGITS
    ஏ
    1.25
    ஆ
    1.20
    অ
    1.11
    அ
    1.08
    எ
    1.00
     نوفمبر
    1.00
     Профиль
    1.00
    weichen
    0.99
    Mål
    0.99
    muito
    0.98
    Activations Density 0.021%

    No Known Activations