© 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. 92547
    Prev
    Next
    INDEX
    Explanations

    South Asian and Southeast Asian countries

    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
    ganta
    -0.77
    czyć
    -0.77
     cacao
    -0.74
     replays
    -0.71
    шься
    -0.71
     BaseActivity
    -0.71
     conclusione
    -0.70
    FullName
    -0.70
    客房
    -0.69
     Conse
    -0.69
    POSITIVE LOGITS
     Bangladesh
    1.11
     افغانستان
    1.04
     Sri
    1.01
     Bhutan
    0.96
     Maldives
    0.96
     Kathmandu
    0.94
     Dhaka
    0.94
    Bangladesh
    0.92
    Afghanistan
    0.91
     Colombo
    0.91
    Activations Density 0.020%

    No Known Activations