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. 5
    Prev
    Next
    INDEX
    Explanations

    code comments and structures

    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
    岀
    -0.85
    ouches
    -0.83
    туаль
    -0.81
    alami
    -0.81
     relev
    -0.78
    ଷ
    -0.78
    onika
    -0.76
     gani
    -0.74
     gráfica
    -0.73
    大门
    -0.73
    POSITIVE LOGITS
    btnut
    0.85
    aito
    0.77
    8
    0.73
    стана
    0.73
    GetHashCode
    0.73
    0
    0.71
    लेट
    0.71
    yty
    0.70
    ヵ
    0.69
    يلات
    0.68
    Activations Density 0.001%

    No Known Activations