© 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. 10-GEMMASCOPE-RES-131K
    7. 112164
    Prev
    Next
    INDEX
    Explanations

    Environmental Protection Agency

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

    references to the Environmental Protection Agency (EPA).

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

    The neuron activates on mentions of the U.S. Environmental Protection Agency, especially the acronym “EPA.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     
    -2.92
     mesmerizing
    -2.73
     VERY
    -2.69
    </h2>
    -2.61
     predominantly
    -2.59
     veritable
    -2.56
     alluring
    -2.52
    1
    -2.52
     Provides
    -2.48
    </em>
    -2.47
    POSITIVE LOGITS
    🌼
    3.05
    🤓
    2.98
    🥶
    2.97
    💓
    2.84
    🎃
    2.83
    😈
    2.80
    🌻
    2.78
    👽
    2.67
    🤤
    2.66
    💞
    2.66
    Activations Density 0.009%

    No Known Activations