© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34126
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people

    np_acts-logits-general · gemini-2.5-flash-lite

    pronouns and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ဂ
    0.48
    cac
    0.46
     Fittings
    0.46
    களில்
    0.46
     ဂ
    0.44
    羯
    0.44
    ീസ്
    0.43
     giriş
    0.43
     காணப்படும்
    0.43
    웍
    0.43
    POSITIVE LOGITS
     himself
    0.77
     him
    0.76
     ему
    0.75
     उसे
    0.73
     его
    0.70
     his
    0.69
     उसको
    0.68
     jego
    0.66
     його
    0.64
     তাকে
    0.62
    Activations Density 0.172%

    No Known Activations