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. 8475
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

    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
     է
    -0.81
    ◜
    -0.81
    祠
    -0.81
     洋
    -0.77
     even
    -0.76
     could
    -0.73
     सभी
    -0.72
    tious
    -0.71
    ও
    -0.70
     okol
    -0.69
    POSITIVE LOGITS
    чної
    0.90
     Szw
    0.88
     jaki
    0.82
    झ
    0.82
     conseils
    0.82
     piaci
    0.81
    付
    0.81
     chert
    0.79
     nether
    0.79
     CER
    0.78
    Activations Density 0.035%

    No Known Activations