© 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. 71717
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by object

    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
     possono
    -1.73
    wasn
    -1.59
    罽
    -1.56
    踯
    -1.51
    ironically
    -1.51
    鬭
    -1.48
    縢
    -1.45
     pollici
    -1.44
     the
    -1.43
     voglio
    -1.43
    POSITIVE LOGITS
     people
    1.75
    龊
    1.63
     Wartawan
    1.59
     of
    1.57
     επίσης
    1.48
    ࿚
    1.48
     lovers
    1.48
    CHREIB
    1.46
    Another
    1.44
     Bewohner
    1.42
    Activations Density 0.031%

    No Known Activations