© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11527
    Prev
    Next
    INDEX
    Explanations

    się bawić, się ubierać, się podobać

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

    Polish reflexive pronoun się

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    📩
    0.45
    炬
    0.44
     المنتخب
    0.43
    朱
    0.41
     CLIENTI
    0.40
    Chooser
    0.40
    搧
    0.39
    ዦ
    0.39
     Endocrinol
    0.39
    ার্থী
    0.38
    POSITIVE LOGITS
    creative
    0.40
     Sahara
    0.40
    ins
    0.39
    uah
    0.39
    üns
    0.38
     সামান্য
    0.38
     impervious
    0.38
    cont
    0.38
    haven
    0.38
     hall
    0.37
    Activations Density 0.000%

    No Known Activations