© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15298
    Prev
    Next
    INDEX
    Explanations

    lithuania and vilnius

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

    Lithuania and Baltic states

    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
     Souza
    0.55
     Đế
    0.53
    綦
    0.52
     Operand
    0.51
    腧
    0.50
     अफ्री
    0.49
     sổ
    0.49
     પેટ્રોલ
    0.49
     Yucatán
    0.48
    羥
    0.48
    POSITIVE LOGITS
     Lithuanian
    1.22
     Latvian
    1.10
     Lithuania
    1.05
     Vilnius
    1.02
     Latvia
    0.96
     Latvij
    0.92
     Lietuvos
    0.91
    ė
    0.85
     Baltic
    0.82
     Riga
    0.79
    Activations Density 0.021%

    No Known Activations