© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7075
    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-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    kenalkan
    1.80
     unmistakable
    1.79
     Remington
    1.71
    icano
    1.68
     aclar
    1.67
    APPROVED
    1.66
    τικ
    1.65
     competente
    1.65
    浧
    1.63
     وسهلا
    1.63
    POSITIVE LOGITS
    sores
    1.05
     genug
    1.03
    rets
    1.01
     deeds
    0.99
    Supp
    0.99
     wounds
    0.92
    lat
    0.92
     myocardium
    0.92
     irreparable
    0.90
    /}{
    0.88
    Activations Density 0.105%

    No Known Activations