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. 8440
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     eight
    -0.83
    できるので
    -0.79
    オ
    -0.78
     four
    -0.77
    正義
    -0.77
     six
    -0.77
     you
    -0.77
    jones
    -0.77
    entra
    -0.76
     nine
    -0.75
    POSITIVE LOGITS
     lendemain
    0.91
    Fits
    0.90
     olacaktır
    0.88
     indent
    0.84
    judul
    0.82
    ୍
    0.81
    verhalten
    0.80
     progresso
    0.80
     trabajos
    0.79
    formatting
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.