© 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. 92834
    Prev
    Next
    INDEX
    Explanations

    agglutinative language formation

    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
     업
    0.44
     Things
    0.43
     तीन
    0.42
    planting
    0.40
    传
    0.40
     друго
    0.39
     Ā
    0.39
     레드
    0.39
     رسم
    0.39
     средства
    0.39
    POSITIVE LOGITS
     ngunit
    0.56
    カフェ
    0.45
     fluvial
    0.43
     Nhưng
    0.43
     પરંતુ
    0.42
    ǀ
    0.42
     lakini
    0.42
    लेकिन
    0.41
    لیکن
    0.41
     isolated
    0.41
    Activations Density 0.014%

    No Known Activations