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. 228
    Prev
    Next
    INDEX
    Explanations

    markup and code structures

    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
     muitas
    -0.82
    şı
    -0.82
    itures
    -0.79
    oué
    -0.78
    arraycopy
    -0.78
    Boh
    -0.77
     snare
    -0.76
    Kiwi
    -0.76
     muitos
    -0.76
    anadas
    -0.76
    POSITIVE LOGITS
     here
    1.02
     nuevos
    0.88
     église
    0.87
    buch
    0.85
     before
    0.85
     grosir
    0.82
     sembrano
    0.81
    <h4>
    0.81
    Exceeded
    0.79
     endian
    0.78
    Activations Density 0.017%

    No Known Activations