© 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. 2950
    Prev
    Next
    INDEX
    Explanations

    insects and mosquitoes

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

    terms related to insects, particularly mosquitoes and disease vectors.

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

    The neuron flags insect‐ and mosquito‐related terms (e.g. “insect,” “bites,” “mosquito,” “insecticidal,” etc.).

    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
    bao
    -0.85
     fría
    -0.84
    clus
    -0.82
    orative
    -0.82
    olation
    -0.81
    海底
    -0.80
    opra
    -0.79
    dige
    -0.78
    底下
    -0.78
     monetary
    -0.75
    POSITIVE LOGITS
     mosquito
    2.52
     mosquitoes
    2.45
    Mosquito
    2.22
     Mosquito
    2.13
     mosquitos
    1.84
    蚊
    1.66
     repel
    1.54
     repellent
    1.53
     insect
    1.51
     Insect
    1.43
    Activations Density 0.026%

    No Known Activations