© 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. 16-GEMMASCOPE-2-RES-262K
    7. 116483
    Prev
    Next
    INDEX
    Explanations

    Korean, Chinese, Vietnamese related to connection or union

    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_16_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
    ра
    1.38
    ى
    1.28
    า
    1.23
    ור
    1.20
    ா
    1.18
    ру
    1.14
    ки
    1.09
    но
    1.09
    ا
    1.05
    ാ
    1.04
    POSITIVE LOGITS
    t
    1.80
     be
    1.20
    w
    1.14
    SF
    1.05
    고
    1.05
    OP
    1.04
    MV
    1.01
    tä
    1.00
    IN
    0.99
     correlates
    0.98
    Activations Density 0.002%

    No Known Activations