© 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. 10-GEMMASCOPE-RES-131K
    7. 68914
    Prev
    Next
    INDEX
    Explanations

    possessives followed by nouns

    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_10/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
     offrent
    -1.55
     blanda
    -1.55
    Already
    -1.48
     mereka
    -1.47
    镡
    -1.46
     INSTRUMENTS
    -1.44
     GONNA
    -1.41
    already
    -1.35
     nieve
    -1.34
    将其
    -1.33
    POSITIVE LOGITS
     to
    1.98
     todėl
    1.87
     \
    1.70
    ↵
    1.51
    ,
    1.25
    和小
    1.23
    Mvh
    1.23
    ϱ
    1.23
    rodalom
    1.22
    dây
    1.20
    Activations Density 0.054%

    No Known Activations