© 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. 34-GEMMASCOPE-RES-131K
    7. 78321
    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_34/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
    лько
    -0.88
    eschou
    -0.81
     Acceler
    -0.80
    ()]
    -0.79
    Matchers
    -0.78
    Мы
    -0.78
     Мы
    -0.78
    θρω
    -0.77
    テール
    -0.77
    rimir
    -0.77
    POSITIVE LOGITS
     seus
    2.55
     his
    2.53
     своих
    2.52
     свої
    2.31
     swoich
    2.30
     their
    1.97
     अपने
    1.96
     its
    1.92
     your
    1.77
     my
    1.76
    Activations Density 0.116%

    No Known Activations