© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103016
    Prev
    Next
    INDEX
    Explanations

    exposure duration and context

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

    phrases related to exposure to substances, particularly in medical or scientific contexts.

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

    The neuron detects mentions of “exposure” (especially qualified by duration or context, like long-term, prolonged, occupational, or previous exposure).

    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
     TEACHING
    -0.85
    回る
    -0.79
    ADP
    -0.77
    вою
    -0.77
     Giro
    -0.76
     ADP
    -0.74
    förder
    -0.73
    ストン
    -0.73
    レッ
    -0.73
    ウス
    -0.71
    POSITIVE LOGITS
     exposure
    6.13
    exposure
    4.88
     Exposure
    4.84
    Exposure
    4.72
     exposed
    4.16
     EXPOSURE
    3.84
     exposures
    3.83
    exposed
    3.73
     expose
    3.66
     exposición
    3.44
    Activations Density 0.157%

    No Known Activations