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. 112
    Prev
    Next
    INDEX
    Explanations

    foreign direct investment proposals

    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
    enaar
    -0.75
     kväll
    -0.71
    Gebruik
    -0.69
    mainPanel
    -0.68
    𝐲
    -0.67
     conosce
    -0.67
     aspet
    -0.67
     nörd
    -0.67
     madres
    -0.66
    álja
    -0.66
    POSITIVE LOGITS
     FDI
    1.49
    ALLOWED
    0.92
     Retail
    0.92
     foreign
    0.87
    允许
    0.85
    Whitney
    0.84
     Wholesale
    0.82
     inviting
    0.82
     допуска
    0.81
     automatic
    0.81
    Activations Density 0.017%

    No Known Activations