© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 73886
    Prev
    Next
    INDEX
    Explanations

    Borneo and Brunei locations

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

    Borneo, Alaska, native peoples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     আইডিয়া
    0.46
    富士
    0.45
     आक्रोश
    0.45
     lactis
    0.45
     Charlottesville
    0.43
     ቫ
    0.43
    镐
    0.43
    聁
    0.43
     Há
    0.42
    ottesville
    0.42
    POSITIVE LOGITS
     Sarawak
    0.82
     Borneo
    0.76
     Kalimantan
    0.61
     Montana
    0.52
    Montana
    0.52
     Alaskan
    0.50
     Sabah
    0.50
     paddle
    0.49
     Brunei
    0.47
     Alaska
    0.45
    Activations Density 0.025%

    No Known Activations