Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8616
    Prev
    Next
    INDEX
    Explanations

    version 3 of the 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
    邛
    -0.86
     insbesondere
    -0.83
    masters
    -0.81
     naudoti
    -0.77
    斯的
    -0.75
    🪘
    -0.74
    Caribbean
    -0.73
     πυ
    -0.73
    āv
    -0.73
    ᯽
    -0.73
    POSITIVE LOGITS
    https
    0.91
    ソナ
    0.91
     кнопки
    0.85
    Accessed
    0.82
    тились
    0.81
     фильтра
    0.80
    과
    0.77
     физи
    0.76
     sickening
    0.76
     finalidad
    0.75
    Activations Density 0.005%

    No Known Activations