© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82333
    Prev
    Next
    INDEX
    Explanations

    sunrise and sunset

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

    This neuron signals when the text mentions warm, color-rich lighting or times of day—especially “golden hour” cues like sunrise, sunset, golden, magical light, etc.

    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
     ultrason
    -0.93
     impuls
    -0.84
     resourceCulture
    -0.78
    ropho
    -0.78
     Humana
    -0.77
    Hurricane
    -0.75
    шки
    -0.75
    üße
    -0.75
    Overflow
    -0.74
    Snow
    -0.74
    POSITIVE LOGITS
     sunset
    3.17
     sunsets
    2.63
    sunset
    2.17
     Sunset
    1.99
    Sunset
    1.92
     sunrise
    1.73
    🌅
    1.63
    夕
    1.50
     sundown
    1.46
    sunrise
    1.29
    Activations Density 0.016%

    No Known Activations