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. 8102
    Prev
    Next
    INDEX
    Explanations

    csv files, weather, datasets

    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
     regardless
    -0.78
    ウンド
    -0.76
     Eurosport
    -0.76
     replaceable
    -0.74
     on
    -0.72
     detachable
    -0.71
    containers
    -0.69
    ዱ
    -0.69
     implementar
    -0.69
    🧮
    -0.69
    POSITIVE LOGITS
     dataset
    1.36
     Kag
    0.99
     CSV
    0.97
    csv
    0.95
     csv
    0.93
    dataset
    0.91
     data
    0.91
     Billion
    0.90
     sample
    0.90
     NYC
    0.88
    Activations Density 0.043%

    No Known Activations