© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 256
    Prev
    Next
    INDEX
    Explanations

    insects and pests

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

    terms related to pests, insects, and plant protection.

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

    The neuron activates on terms related to insects and pest control (e.g. “insects,” “infestation,” “insecticides,” “resistance to 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
     Souza
    -0.76
     voiture
    -0.74
     django
    -0.73
     JComboBox
    -0.72
     humains
    -0.71
     الأشخاص
    -0.71
     Eduard
    -0.71
     penderita
    -0.70
    iados
    -0.69
    Prof
    -0.69
    POSITIVE LOGITS
     pests
    3.31
     insects
    3.23
     insect
    3.08
     pest
    2.95
     bugs
    2.59
    虫
    2.38
     Insects
    2.33
     bug
    2.30
    insect
    2.27
     Pests
    2.25
    Activations Density 0.056%

    No Known Activations