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. 8474
    Prev
    Next
    INDEX
    Explanations

    code and math expressions

    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
     handful
    -0.87
    älle
    -0.84
    摺
    -0.83
    ‪
    -0.80
    編曲
    -0.80
    Cerca
    -0.77
     CGRectMake
    -0.75
    (…)
    -0.75
     boar
    -0.74
     situa
    -0.74
    POSITIVE LOGITS
     puisi
    0.88
    で使用
    0.86
    animo
    0.84
    lamic
    0.84
    jess
    0.83
    inspec
    0.83
     peningkatan
    0.81
     nutrisi
    0.81
     alanı
    0.81
     sesuatu
    0.80
    Activations Density 0.002%

    No Known Activations