© 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. 59122
    Prev
    Next
    INDEX
    Explanations

    bed bugs

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

    mentions of insects and pests, particularly bed bugs and parasitic bugs.

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

    The neuron activates strongly on Latin scientific (binomial) species 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
     kidneys
    -0.83
    不由得
    -0.81
     forklift
    -0.77
     Knuckles
    -0.77
     編集
    -0.75
    ческим
    -0.75
     paternal
    -0.72
     slugs
    -0.71
     nejak
    -0.69
     corruption
    -0.69
    POSITIVE LOGITS
     infestations
    1.03
     lice
    1.03
     infested
    1.01
     infestation
    1.00
     bed
    0.97
     infest
    0.89
     treatment
    0.87
     Lice
    0.85
    رشف
    0.81
    hime
    0.81
    Activations Density 0.017%

    No Known Activations