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. 8355
    Prev
    Next
    INDEX
    Explanations

    code comments and math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     يريد
    -0.81
    werf
    -0.81
    赛事
    -0.81
     хотят
    -0.78
    tactos
    -0.77
    wargs
    -0.77
    Protobuf
    -0.77
    SUCCEEDED
    -0.77
    stopp
    -0.76
    фикация
    -0.75
    POSITIVE LOGITS
    +
    1.13
    @@
    0.88
    +</
    0.87
     особенно
    0.83
    -
    0.82
     IPv
    0.82
     especialmente
    0.79
     antifungal
    0.78
     quizás
    0.75
     +
    0.72
    Activations Density 0.021%

    No Known Activations