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. 220
    Prev
    Next
    INDEX
    Explanations

    expressing thanks

    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
     as
    -1.18
     консер
    -0.90
     Некоторые
    -0.84
     Особенно
    -0.83
    というのも
    -0.83
     chuyền
    -0.82
     some
    -0.79
    がありません
    -0.78
    Long
    -0.78
     similarly
    -0.76
    POSITIVE LOGITS
     alot
    1.47
    alot
    1.41
     большое
    1.21
     beaucoup
    1.18
     anyway
    1.05
     lot
    1.05
    มาก
    1.00
     всичко
    0.98
     nhiều
    0.96
     مرة
    0.94
    Activations Density 0.026%

    No Known Activations