© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5052
    Prev
    Next
    INDEX
    Explanations

    possessive particle/article ('de', '的')

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ী
    0.96
     වඩා
    0.85
    categorias
    0.78
    または
    0.78
     sûr
    0.74
    fahren
    0.73
    ية
    0.73
    t
    0.72
    дете
    0.71
    ន៍
    0.70
    POSITIVE LOGITS
    .
    1.13
    '
    1.04
    ’
    0.93
    的
    0.90
    ,
    0.83
    ?
    0.80
    af
    0.77
    !
    0.77
     sayesinde
    0.75
    ভাই
    0.72
    Activations Density 0.010%

    No Known Activations