© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4188
    Prev
    Next
    INDEX
    Explanations

    possessive structure marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Their
    -1.24
    their
    -1.15
     leurs
    -1.09
    のよう
    -1.07
    的食物
    -1.04
    嘣
    -0.98
    的目的
    -0.98
     themselves
    -0.97
    のひとつ
    -0.97
    álu
    -0.97
    POSITIVE LOGITS
    의
    3.61
     of
    3.52
     的
    3.25
    的
    2.94
    嘅
    2.33
    の
    2.25
    的小
    2.17
    的一
    2.13
    的大
    2.02
    のお
    1.93
    Activations Density 0.009%

    No Known Activations