© 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. 181498
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

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

    possessive pronouns in multiple languages

    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
    民
    0.44
     fools
    0.38
    ımızı
    0.38
     පමණ
    0.38
     Stair
    0.38
    था
    0.37
     után
    0.37
    Mình
    0.37
     민
    0.36
    stedt
    0.36
    POSITIVE LOGITS
    她的
    1.00
     jego
    0.95
    他的
    0.93
    了他的
    0.92
     njegov
    0.90
     его
    0.88
     उसकी
    0.87
     그의
    0.87
     його
    0.85
     அவரது
    0.84
    Activations Density 0.004%

    No Known Activations