© 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. 22-GEMMASCOPE-RES-131K
    7. 33880
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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_22/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
     of
    -0.94
     kendini
    -0.93
     språk
    -0.90
    activités
    -0.86
     Biv
    -0.85
    ragona
    -0.85
    Nu
    -0.85
     for
    -0.83
    クタ
    -0.82
    它的
    -0.81
    POSITIVE LOGITS
     their
    2.41
     jejich
    1.63
     их
    1.48
    Their
    1.48
     leurs
    1.47
     leur
    1.46
     they
    1.41
    their
    1.40
     mereka
    1.34
    他們
    1.33
    Activations Density 0.035%

    No Known Activations