© 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. 34557
    Prev
    Next
    INDEX
    Explanations

    geographical locations and context

    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
     Barcode
    -0.75
    acheco
    -0.71
     komende
    -0.69
     Imports
    -0.67
     Loans
    -0.66
    DateTimePicker
    -0.65
    عر
    -0.65
     Kig
    -0.65
     Unterhaltung
    -0.63
     anstatt
    -0.63
    POSITIVE LOGITS
     City
    1.17
     city
    1.13
     Geo
    1.13
     COUNTRY
    1.09
     Country
    1.09
     country
    1.08
    City
    1.01
    city
    1.00
     ISP
    0.99
    ISP
    0.95
    Activations Density 0.007%

    No Known Activations