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. 222
    Prev
    Next
    INDEX
    Explanations

    copyright and license

    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
     Prozent
    -0.96
    </em>
    -0.86
     any
    -0.84
    </
    -0.82
     their
    -0.81
     pire
    -0.81
     pengurus
    -0.78
     Мор
    -0.77
    рю
    -0.77
    нией
    -0.77
    POSITIVE LOGITS
    <table>
    1.04
    显示
    0.98
     інформа
    0.89
    까지
    0.88
     though
    0.88
    видео
    0.85
    ndar
    0.85
    章节错误
    0.85
    cabul
    0.83
    QUEST
    0.82
    Activations Density 0.064%

    No Known Activations