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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7880
    Prev
    Next
    INDEX
    Explanations

    this week or month

    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
     YEARS
    -0.96
     vuonna
    -0.94
    years
    -0.94
    собенности
    -0.93
    året
    -0.93
    year
    -0.89
     Estos
    -0.87
    出版年
    -0.86
     algún
    -0.86
    These
    -0.85
    POSITIVE LOGITS
     this
    4.59
     week
    2.75
    this
    2.09
     today
    1.91
     month
    1.83
     αυτή
    1.75
     этой
    1.75
     цього
    1.71
     этого
    1.70
     هذا
    1.69
    Activations Density 0.111%

    No Known Activations