© 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. 79130
    Prev
    Next
    INDEX
    Explanations

    social bees and wasps

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

    taxonomic classifications of insects, particularly focusing on hymenoptera (bees, wasps, ants) species names and terminology.

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

    This neuron detects scientific taxonomic names (particularly Latin genus and family names) of insects.

    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
    木村
    -0.80
    arja
    -0.75
     آمار
    -0.71
    本田
    -0.70
     kỹ
    -0.69
     φο
    -0.68
    strophic
    -0.68
    idet
    -0.67
    vascular
    -0.67
     steamers
    -0.67
    POSITIVE LOGITS
     bees
    1.30
     pollen
    1.23
     bee
    1.12
     Bee
    1.00
     nesting
    0.97
     Bees
    0.93
    🐝
    0.92
     BEE
    0.90
     solitary
    0.86
    bees
    0.85
    Activations Density 0.049%

    No Known Activations