© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23410
    Prev
    Next
    INDEX
    Explanations

    foreign language identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —
    0.45
    ạy
    0.42
    激动
    0.42
    ći
    0.41
    ça
    0.40
     sărb
    0.40
    мышлен
    0.39
    мыш
    0.39
    ้าม
    0.38
    ιών
    0.38
    POSITIVE LOGITS
     صفح
    0.47
     unsere
    0.45
     ಕಂಪ
    0.44
     unserem
    0.43
     ನಾವು
    0.42
    我們的
    0.42
     nostra
    0.42
     longitudine
    0.41
     同
    0.41
     recta
    0.41
    Activations Density 0.000%

    No Known Activations