Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 42
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post
    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
    in
    0.71
    ح
    0.56
     .
    0.55
     in
    0.54
     is
    0.53
    itude
    0.52
    ль
    0.52
     to
    0.52
    arı
    0.49
    し
    0.49
    POSITIVE LOGITS
     அமைந்துள்ள
    0.53
     aktivnosti
    0.49
     ofrec
    0.48
     gerar
    0.47
     파일
    0.47
    პ
    0.46
    ак
    0.46
     নিত
    0.46
     azione
    0.45
    рих
    0.45
    Activations Density 3.362%

    No Known Activations