© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59516
    Prev
    Next
    INDEX
    Explanations

    hazardous waste disposal

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

    references to hazardous waste and waste disposal facilities.

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

    The neuron activates on mentions of waste disposal or hazardous‐waste management (e.g., “radioactive waste,” “hazardous products,” “disposal,” 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
    pendicular
    -0.84
    orescence
    -0.79
     artificial
    -0.74
     аллер
    -0.73
     künst
    -0.73
    tilization
    -0.71
    Artificial
    -0.71
    utrients
    -0.69
    ！！」
    -0.69
    フォーマ
    -0.69
    POSITIVE LOGITS
     hazardous
    1.43
     manifest
    1.36
     Hazardous
    1.21
    manifest
    1.21
    Manifest
    1.18
    Hazardous
    1.18
     Manifest
    1.16
     drums
    1.10
     waste
    1.07
     cradle
    1.02
    Activations Density 0.023%

    No Known Activations