© 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. 64729
    Prev
    Next
    INDEX
    Explanations

    plant genus and species names

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

    scientific names of plants, particularly Latin taxonomic terms for plant species and genera.

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

    This neuron detects scientific plant names (Latin genus and species terms) in the text.

    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
     зелё
    -0.88
     oliva
    -0.88
    женный
    -0.88
    ֠
    -0.83
    という感じ
    -0.82
     nấm
    -0.81
    意識
    -0.81
     птицы
    -0.80
    olev
    -0.79
    講師
    -0.77
    POSITIVE LOGITS
    wort
    1.13
    ijų
    0.86
    Garry
    0.83
    rape
    0.81
     vencedor
    0.81
     perennial
    0.80
    root
    0.79
     bitter
    0.79
    เทศ
    0.79
    Werk
    0.78
    Activations Density 0.067%

    No Known Activations