© 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. 45570
    Prev
    Next
    INDEX
    Explanations

    daily sunshine hours

    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
     leave
    -0.71
    食べたい
    -0.68
    ̓
    -0.67
    nalités
    -0.67
     lasciare
    -0.66
     Dalam
    -0.66
    party
    -0.65
    macos
    -0.65
     party
    -0.65
     warmer
    -0.65
    POSITIVE LOGITS
     clearness
    1.45
     clears
    0.97
    Clear
    0.93
     irradiation
    0.91
     CLEAR
    0.90
     Clear
    0.88
     kWh
    0.88
     hourly
    0.88
     clear
    0.87
     hours
    0.85
    Activations Density 0.005%

    No Known Activations