© 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. 211980
    Prev
    Next
    INDEX
    Explanations

    construction and performance

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

    established categories

    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
     objetos
    0.53
    igkeiten
    0.46
    ندوق
    0.45
     tats
    0.45
     objets
    0.45
    واع
    0.44
     equipamentos
    0.44
    なのです
    0.44
    اتي
    0.43
    팅
    0.43
    POSITIVE LOGITS
     ብዙውን
    0.52
     週
    0.47
    site
    0.45
     reside
    0.44
     ലക്ഷ
    0.44
     കൂടുതല്‍
    0.43
     monta
    0.43
     `<=`
    0.43
    ḷ
    0.43
    another
    0.42
    Activations Density 0.001%

    No Known Activations