© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10426
    Prev
    Next
    INDEX
    Explanations

    Lithuanian and Latvian place names

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

    Lithuania, Vytautas, Baltic, Supabase, VPN

    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_40_width_16k_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
     છ
    0.55
     پسر
    0.54
     نشست
    0.51
     بالاتر
    0.50
     درخواست
    0.50
     چنان
    0.50
     фараз
    0.49
     بچه
    0.49
     درمان
    0.49
     マルチ
    0.48
    POSITIVE LOGITS
     Lithuanian
    1.62
     Lithuania
    1.53
     Vilnius
    1.44
     Lietuvos
    1.42
    ė
    1.18
     літоў
    1.16
     Latvian
    1.16
     Latvia
    1.12
    Lith
    1.02
     Latvij
    1.02
    Activations Density 0.056%

    No Known Activations