© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3298
    Prev
    Next
    INDEX
    Explanations

    urban heat, city, street dust

    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
     Illumination
    -0.92
    imek
    -0.85
     SharePoint
    -0.83
    Transk
    -0.83
    谥
    -0.79
     luminos
    -0.76
    ▣
    -0.76
    InitialState
    -0.75
     reais
    -0.75
     controver
    -0.75
    POSITIVE LOGITS
     urban
    2.23
    Urban
    1.92
     Urban
    1.88
     city
    1.78
    urban
    1.72
     heat
    1.55
    City
    1.46
     City
    1.41
    Heat
    1.40
    城市
    1.38
    Activations Density 0.019%

    No Known Activations