© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82980
    Prev
    Next
    INDEX
    Explanations

    continents and regions

    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
    荷兰
    -1.05
     افغان
    -0.94
     Estonian
    -0.94
    ָם
    -0.94
    Nation
    -0.92
     нарушения
    -0.86
    Opere
    -0.85
     włosów
    -0.84
    grafa
    -0.83
     خارجية
    -0.82
    POSITIVE LOGITS
     Europe
    4.28
     Asia
    4.25
     Americas
    3.25
     Africa
    3.16
    Asia
    3.13
    Europe
    2.95
     North
    2.70
     European
    2.69
     Asian
    2.59
     asia
    2.58
    Activations Density 0.137%

    No Known Activations