© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58253
    Prev
    Next
    INDEX
    Explanations

    UV rays and exposure

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

    references to ultraviolet (UV) radiation and sunlight, particularly in the context of protection or exposure effects.

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

    This neuron detects mentions of ultraviolet (UV) or sun‐protection features (e.g., blocking, reflecting, or filtering harmful UV rays).

    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
    ighed
    -0.78
    йся
    -0.77
     المعل
    -0.75
    eaks
    -0.74
    eaa
    -0.72
    falcon
    -0.71
    flowing
    -0.70
    Pwd
    -0.69
    ㎍
    -0.68
    imler
    -0.67
    POSITIVE LOGITS
     rays
    3.70
    rays
    2.48
     Rays
    2.36
     ray
    2.05
    Rays
    1.87
     UV
    1.85
     rayos
    1.75
    ray
    1.67
     ultraviolet
    1.66
     rayons
    1.63
    Activations Density 0.020%

    No Known Activations