© 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. 115833
    Prev
    Next
    INDEX
    Explanations

    vitamin D and sunlight

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

    mentions of vitamin D in scientific or medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Freeze
    -0.81
    Freeze
    -0.80
    ản
    -0.77
     Linn
    -0.75
    Kali
    -0.75
     เย
    -0.74
     wine
    -0.72
     cuivre
    -0.72
    Gustav
    -0.70
     scelto
    -0.70
    POSITIVE LOGITS
     UVB
    1.34
     sunlight
    1.11
     sunshine
    1.02
     Sunlight
    0.91
     Hügel
    0.89
     bone
    0.86
     sunny
    0.85
    ufficient
    0.84
     insufficiency
    0.84
     latitude
    0.82
    Activations Density 0.037%

    No Known Activations