© 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. 57714
    Prev
    Next
    INDEX
    Explanations

    urban city descriptions and associated creators

    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
    κης
    -1.02
    TagHelper
    -0.98
    骼
    -0.96
    istorante
    -0.95
     campsites
    -0.94
     chalet
    -0.94
    tocks
    -0.94
     farmhouse
    -0.94
     Campground
    -0.92
    resher
    -0.90
    POSITIVE LOGITS
     city
    3.73
     street
    3.16
     urban
    3.08
     streets
    2.69
    city
    2.55
     City
    2.52
    City
    2.48
    urban
    2.25
     downtown
    2.23
     CITY
    2.17
    Activations Density 0.143%

    No Known Activations