© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20482
    Prev
    Next
    INDEX
    Explanations

    symbols and foreign words

    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
    复
    0.47
    gek
    0.47
    न
    0.46
     Idani
    0.45
    처럼
    0.44
    ர்
    0.44
     পাশ্চাত্য
    0.44
    -
    0.44
     आढळ
    0.42
     extranjero
    0.42
    POSITIVE LOGITS
     ପ୍ର
    0.45
     meals
    0.40
    ಲಾಗುತ್ತದೆ
    0.40
     συγκεκρι
    0.39
     столи
    0.38
     inlaid
    0.38
     cursory
    0.38
    Trademark
    0.38
     使っ
    0.38
     food
    0.38
    Activations Density 0.001%

    No Known Activations