© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31228
    Prev
    Next
    INDEX
    Explanations

    weather forecasts for cities

    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
     alluded
    -0.77
    ölkerung
    -0.77
    ťa
    -0.77
    说过
    -0.74
    enschap
    -0.74
    orderItem
    -0.73
     Quantification
    -0.72
     îles
    -0.71
    ProductCategory
    -0.71
    razio
    -0.70
    POSITIVE LOGITS
     forecast
    1.93
     city
    1.66
     forecasts
    1.45
    forecast
    1.44
     cities
    1.40
    city
    1.32
     weather
    1.31
     location
    1.31
     città
    1.31
     Forecast
    1.30
    Activations Density 0.019%

    No Known Activations