© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75619
    Prev
    Next
    INDEX
    Explanations

    fungus and fungal genera

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

    names of fungal species and genera in scientific/research contexts.

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

    The neuron strongly activates on long, technical scientific terms—especially Latin binomials (genus/species names) and complex biochemical or compound names.

    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
    ক্ত
    -0.78
    Auth
    -0.74
    Sul
    -0.73
     Matri
    -0.73
    суль
    -0.73
     SITE
    -0.71
     Sul
    -0.71
    SITE
    -0.69
    HasColumn
    -0.69
    セリ
    -0.69
    POSITIVE LOGITS
     Fusarium
    1.12
     fungal
    1.08
     fungi
    1.02
     Aspergillus
    1.00
     fungus
    0.97
     cultures
    0.91
     mold
    0.91
    fung
    0.90
     doth
    0.89
     mould
    0.86
    Activations Density 0.151%

    No Known Activations