© 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. 50069
    Prev
    Next
    INDEX
    Explanations

    Russian place names

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

    stress in pronunciation

    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
    퓰
    0.50
    分からない
    0.47
    лимпиа
    0.47
    ம்தா
    0.46
    ᒧ
    0.46
    姮
    0.44
    molecule
    0.43
    톈
    0.42
    Bibli
    0.41
    HIV
    0.41
    POSITIVE LOGITS
     dies
    0.48
    rigues
    0.45
     gladi
    0.45
     smelting
    0.45
    4
    0.45
     camps
    0.44
     Wisconsin
    0.44
     fighters
    0.44
     brooding
    0.44
     sung
    0.43
    Activations Density 0.001%

    No Known Activations