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. 48
    Prev
    Next
    INDEX
    Explanations

    under 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
    знес
    -0.72
    insular
    -0.68
     Grenz
    -0.63
    border
    -0.63
    limit
    -0.62
     limit
    -0.62
    Volatile
    -0.61
     بتاريخ
    -0.60
     Triangle
    -0.60
     ok
    -0.60
    POSITIVE LOGITS
     Sumber
    0.77
     TEMPLATE
    0.73
     Abo
    0.72
    嘸
    0.71
    дравству
    0.71
    andinav
    0.70
    ~$\
    0.70
     Quil
    0.69
    钇
    0.69
     مطال
    0.69
    Activations Density 0.069%

    No Known Activations