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. 115
    Prev
    Next
    INDEX
    Explanations

    lists of top performers

    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
     certificación
    -0.84
    確認ください
    -0.82
    ecake
    -0.81
     koszulka
    -0.78
     mojej
    -0.77
     feveral
    -0.77
     estadía
    -0.77
    ierre
    -0.77
    ชุด
    -0.77
     męskie
    -0.77
    POSITIVE LOGITS
     overall
    1.28
     in
    1.20
     for
    0.98
     seda
    0.96
     awakeFromNib
    0.94
    Overall
    0.91
    hdysval
    0.90
     Overall
    0.87
    ategori
    0.85
     América
    0.85
    Activations Density 0.035%

    No Known Activations