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. 8241
    Prev
    Next
    INDEX
    Explanations

    subduction zone geology

    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
     tables
    -0.98
    tables
    -0.88
    Tables
    -0.87
    TABLES
    -0.81
     impost
    -0.79
     table
    -0.77
     навы
    -0.76
     جدول
    -0.74
    íferos
    -0.74
    loth
    -0.73
    POSITIVE LOGITS
     trench
    1.23
     trenches
    1.10
     Trench
    0.93
    俯
    0.89
     Wad
    0.88
     Tren
    0.85
     convergent
    0.84
     Naz
    0.82
     arc
    0.81
    tren
    0.80
    Activations Density 0.017%

    No Known Activations