© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32424
    Prev
    Next
    INDEX
    Explanations

    Libya and North Africa

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of specific geographic locations or place names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Telangana
    -0.76
     actrices
    -0.72
    雛
    -0.71
    зовый
    -0.69
    ⒏
    -0.69
     CRL
    -0.68
     Paragu
    -0.68
     sā
    -0.68
    гло
    -0.68
     Galicia
    -0.68
    POSITIVE LOGITS
     Libya
    2.80
     Libyan
    2.69
    Libya
    2.23
     Tripoli
    1.70
     Beng
    1.45
     Lib
    1.37
    Lib
    1.30
     ليب
    1.30
     اللي
    1.12
     lib
    1.09
    Activations Density 0.049%

    No Known Activations