© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38788
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns 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
    鼋
    -1.80
    
    -1.77
    ınız
    -1.75
    
    -1.74
     gedrag
    -1.74
     balık
    -1.70
     afbeeldingen
    -1.67
     recibiendo
    -1.65
     resumes
    -1.64
     antics
    -1.64
    POSITIVE LOGITS
    us
    2.25
    te
    2.02
     $\
    1.97
     that
    1.95
    l
    1.92
    r
    1.91
    le
    1.88
     to
    1.85
    li
    1.84
    se
    1.77
    Activations Density 0.021%

    No Known Activations