© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203631
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sui
    0.64
     sien
    0.61
     hi
    0.61
     их
    0.61
     sú
    0.61
     їх
    0.60
    其
    0.57
     其
    0.54
     sei
    0.51
     zij
    0.50
    POSITIVE LOGITS
    自分の
    0.56
     Hers
    0.54
    自分が
    0.50
    hers
    0.48
    自身の
    0.48
    Hers
    0.48
     자신이
    0.47
     নিজের
    0.46
     तिला
    0.46
    あなたの
    0.45
    Activations Density 0.010%

    No Known Activations