© 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. 81529
    Prev
    Next
    INDEX
    Explanations

    artificial light, urban night

    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
     sunshine
    -0.87
     太陽
    -0.84
    რი
    -0.84
    阳光
    -0.81
     sunny
    -0.80
    sunshine
    -0.77
    Lunch
    -0.77
    lunch
    -0.76
    メット
    -0.76
     sun
    -0.75
    POSITIVE LOGITS
     Bort
    1.25
     pollution
    1.09
     tonight
    1.07
     nights
    1.03
     artificial
    1.03
     sky
    1.00
     cities
    0.97
     city
    0.97
    Artificial
    0.96
     urban
    0.95
    Activations Density 0.013%

    No Known Activations