© 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-262K
    7. 250416
    Prev
    Next
    INDEX
    Explanations

    propecia, provera, game of thrones

    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
    Negative Logits
     Figure
    0.50
     بیچ
    0.46
     strewn
    0.44
     automático
    0.43
     harmony
    0.43
     सुविधाजनक
    0.43
     ed
    0.43
     빈
    0.43
    dimensional
    0.42
     Burnu
    0.42
    POSITIVE LOGITS
    正式
    0.52
    ouser
    0.48
    جري
    0.46
    ১৮
    0.45
     offizi
    0.44
    튜브
    0.44
    ieht
    0.44
    ୌ
    0.43
    ട്ട്
    0.43
    uiten
    0.43
    Activations Density 0.001%

    No Known Activations