© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 24983
    Prev
    Next
    INDEX
    Explanations

    taxonomic names

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

    taxonomic classifications in scientific papers (like "Amphibia: Anura" or "Crustacea: Decapoda").

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

    The neuron detects scientific taxonomic names (Latin clade or rank names like orders, families, and classes).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     niedersachsen
    -0.88
     Puja
    -0.87
     filo
    -0.86
     multicolore
    -0.84
    ubereitung
    -0.84
    饪
    -0.82
    형
    -0.82
     giocatore
    -0.82
    ificaciones
    -0.81
     acquisto
    -0.81
    POSITIVE LOGITS
     with
    1.02
    齟
    0.88
    箇
    0.83
     vznik
    0.81
     svě
    0.81
    浮か
    0.79
    莅
    0.78
     preoperative
    0.77
    先は
    0.77
    特長
    0.76
    Activations Density 0.283%

    No Known Activations