© 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. 34-GEMMASCOPE-RES-131K
    7. 79363
    Prev
    Next
    INDEX
    Explanations

    fish and hamsters

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

    scientific terms related to biology and organisms, particularly species names and taxonomic classifications.

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

    The neuron fires on Latin scientific names (genus and species epithets) in biological taxonomy.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    uristic
    -0.81
     Wolves
    -0.79
    handlebars
    -0.79
     Cub
    -0.79
     état
    -0.79
    itoa
    -0.78
    ultas
    -0.78
    núť
    -0.76
     residuos
    -0.75
     SUBJECT
    -0.74
    POSITIVE LOGITS
     pond
    1.69
     koi
    1.45
     Koi
    1.40
     Pond
    1.27
    pond
    1.17
     ponds
    1.11
    Pond
    1.09
    koi
    1.03
    Koi
    0.96
     goldfish
    0.93
    Activations Density 0.008%

    No Known Activations