© 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. 112641
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

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

    possessive pronouns

    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
    各位
    0.40
    Subtract
    0.37
    elseif
    0.36
    会让
    0.36
    标注
    0.35
     cả
    0.35
    让
    0.35
    如果没有
    0.35
    "]):
    0.35
    选择了
    0.35
    POSITIVE LOGITS
     THEIR
    0.95
     njihov
    0.79
     dirinya
    0.77
     ему
    0.76
    their
    0.73
     njemu
    0.73
    他們的
    0.73
    พวกเขา
    0.72
     მათი
    0.72
     pihaknya
    0.72
    Activations Density 0.497%

    No Known Activations