© 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. 1698
    Prev
    Next
    INDEX
    Explanations

    multilingual words

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

    может, cannot, не

    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
    ۔
    0.38
     samoglas
    0.34
     innymi
    0.30
     şeklinde
    0.29
    ။
    0.29
     sehingga
    0.29
     zodat
    0.28
     және
    0.27
    ។
    0.27
     eftersom
    0.27
    POSITIVE LOGITS
     не
    0.38
     we
    0.32
     постара
    0.32
     already
    0.30
     δεν
    0.29
     only
    0.29
     খুব
    0.29
     уже
    0.29
     नहीं
    0.28
     often
    0.28
    Activations Density 0.052%

    No Known Activations