© 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. 34-GEMMASCOPE-RES-131K
    7. 57521
    Prev
    Next
    INDEX
    Explanations

    genus and species names

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

    This neuron detects taxonomic references and scientific names, particularly focusing on plant genus and species names in scientific contexts.

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

    The neuron detects scientific taxonomic terms, especially Latin genus and species names (and related classification labels).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    作战
    -0.93
     apricots
    -0.89
     onyx
    -0.85
    tablero
    -0.84
     orchards
    -0.84
     oliva
    -0.83
    ૉ
    -0.82
    antMatchers
    -0.82
     fishery
    -0.81
    してた
    -0.79
    POSITIVE LOGITS
     plants
    1.67
     plant
    1.59
    Plants
    1.32
    Plant
    1.32
     plantas
    1.20
     PLANTS
    1.19
     botan
    1.16
     растение
    1.14
     botanique
    1.13
     Plant
    1.13
    Activations Density 0.115%

    No Known Activations