© 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. 65539
    Prev
    Next
    INDEX
    Explanations

    eliminate waste and toxins

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

    the neuron detects text related to the elimination, removal, or transport of waste products from biological systems.

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

    The neuron detects formal definitional statements (term-is-the-…) that explain the meaning or process of a concept.

    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
    enties
    -0.86
    razos
    -0.85
     Spontaneous
    -0.83
    missing
    -0.83
    loem
    -0.80
    addAction
    -0.78
     oom
    -0.73
    闍
    -0.73
     רח
    -0.73
    uteur
    -0.73
    POSITIVE LOGITS
     waste
    2.81
     toxins
    2.16
     wastes
    2.09
     Waste
    2.08
    waste
    1.91
    toxins
    1.90
    Waste
    1.88
     toxic
    1.88
     harmful
    1.63
     poisons
    1.49
    Activations Density 0.062%

    No Known Activations