© 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. 64754
    Prev
    Next
    INDEX
    Explanations

    UV light exposure

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

    terms related to ultraviolet radiation and light-based curing or exposure processes.

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

    The neuron strongly responds to numerical measurement tokens (digits and associated units) in technical/scientific contexts.

    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
    angk
    -0.79
     kond
    -0.79
    Zd
    -0.75
     řízení
    -0.71
    Humidity
    -0.70
     hydrophobic
    -0.70
    είται
    -0.70
     Keb
    -0.69
     sprayed
    -0.69
     Jerzy
    -0.68
    POSITIVE LOGITS
     UV
    1.52
    UV
    1.38
     lamp
    1.26
    lamp
    1.08
     lamps
    1.07
    照
    1.06
    紫
    1.00
     Mercury
    0.98
    Exposure
    0.98
    灯
    0.97
    Activations Density 0.068%

    No Known Activations