© 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. 242751
    Prev
    Next
    INDEX
    Explanations

    Russia, Ukraine, and Slavic languages

    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
    bk
    0.52
    actions
    0.51
    serve
    0.50
    ్
    0.48
    iter
    0.48
    give
    0.47
    矯正
    0.47
    id
    0.47
    ATA
    0.46
    a
    0.46
    POSITIVE LOGITS
     Özel
    0.51
     Russians
    0.48
     gleaned
    0.48
     ши
    0.48
     温
    0.48
    ໂຕ
    0.46
     Ար
    0.46
     regalo
    0.46
     ভাই
    0.46
     россий
    0.46
    Activations Density 0.001%

    No Known Activations