© 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. 118028
    Prev
    Next
    INDEX
    Explanations

    sunshine and good weather

    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
     nightly
    -0.95
    versammlung
    -0.89
    Goodnight
    -0.84
    Rainy
    -0.82
    username
    -0.82
    Night
    -0.81
     bedtime
    -0.80
     rých
    -0.79
     expliqué
    -0.79
    acetyl
    -0.79
    POSITIVE LOGITS
     sunshine
    2.53
     sunny
    2.22
     sun
    2.03
    sunshine
    1.81
     Sunshine
    1.72
    sunny
    1.70
     Sunny
    1.66
     SUN
    1.65
    ☀️
    1.58
     солне
    1.53
    Activations Density 0.030%

    No Known Activations