© 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. 119206
    Prev
    Next
    INDEX
    Explanations

    Northern locations and entities

    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
     Southwark
    -0.97
     Geelong
    -0.91
    SOUTH
    -0.91
     Lusaka
    -0.90
     southeastern
    -0.86
    retain
    -0.82
     Southeastern
    -0.79
     Leinster
    -0.78
    tetten
    -0.77
     너
    -0.76
    POSITIVE LOGITS
     Northern
    1.81
     northern
    1.64
    Northern
    1.61
    northern
    1.47
     nord
    1.29
     Northeastern
    1.29
    Northeast
    1.27
     north
    1.27
     North
    1.24
     север
    1.23
    Activations Density 0.076%

    No Known Activations