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. 200
    Prev
    Next
    INDEX
    Explanations

    review following information

    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
     reacting
    -0.81
     Mexicana
    -0.80
     κάν
    -0.79
     Minangkabau
    -0.79
    زو
    -0.78
    &.
    -0.78
     mexicana
    -0.78
     maux
    -0.78
    龙头
    -0.77
    cijas
    -0.77
    POSITIVE LOGITS
    htdocs
    0.82
     Hate
    0.80
    FB
    0.77
     dioses
    0.75
    zine
    0.73
     cuarta
    0.72
    anglement
    0.71
    瀑
    0.71
     por
    0.71
    kubernetes
    0.71
    Activations Density 0.046%

    No Known Activations