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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8014
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zanim
    -1.13
     barva
    -0.94
    ことがあります
    -0.92
     stroj
    -0.91
     hason
    -0.91
    Conclusión
    -0.89
    falgar
    -0.89
    たびに
    -0.88
     Eliminar
    -0.88
    ﺋ
    -0.87
    POSITIVE LOGITS
     {
    1.10
     overview
    0.94
     Ա
    0.94
     Peter
    0.91
    が
    0.90
     Render
    0.89
    lo
    0.88
     Armenian
    0.88
    section
    0.85
    を
    0.85
    Activations Density 0.000%

    No Known Activations