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. 20
    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
    辰
    0.50
    らい
    0.46
    ריה
    0.46
     компанию
    0.45
     North
    0.45
    onesome
    0.45
    iffs
    0.44
    pst
    0.44
    ba
    0.44
    龟
    0.44
    POSITIVE LOGITS
    ᱓
    0.59
     pollutants
    0.58
     utilisent
    0.56
    ا
    0.55
     oksid
    0.54
     downloads
    0.53
    ೪
    0.53
    ।
    0.52
    ३
    0.52
     haloes
    0.52
    Activations Density 0.000%

    No Known Activations