© 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. 34559
    Prev
    Next
    INDEX
    Explanations

    sunrise and sunset times

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     addressed
    -0.81
    雨
    -0.78
    assertSame
    -0.71
    ಭ
    -0.71
     putem
    -0.70
    散
    -0.69
    wijs
    -0.69
     siker
    -0.68
    取
    -0.68
    rps
    -0.66
    POSITIVE LOGITS
     sunrise
    1.48
     Sunrise
    1.27
     sunset
    1.20
    Sunrise
    1.10
     Sunset
    1.03
    Sunset
    0.98
    sunrise
    0.92
     twilight
    0.91
    Twilight
    0.91
    sunset
    0.91
    Activations Density 0.011%

    No Known Activations