© 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. 82655
    Prev
    Next
    INDEX
    Explanations

    location and GPS

    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
    Ukrainian
    -0.77
    肄
    -0.76
    ┃
    -0.72
     },
    -0.70
    bpp
    -0.69
    bonsoir
    -0.69
     blinded
    -0.69
    movie
    -0.69
     الملف
    -0.68
     anger
    -0.68
    POSITIVE LOGITS
     location
    1.27
     Location
    1.20
    location
    1.06
    Location
    1.05
     getLast
    1.00
    精度
    0.99
     GPS
    0.95
    getLast
    0.94
     LOCATION
    0.93
     gps
    0.90
    Activations Density 0.008%

    No Known Activations