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. 8030
    Prev
    Next
    INDEX
    Explanations

    variety names and descriptions

    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
    ifstream
    -0.71
    샘
    -0.70
    끌
    -0.70
     Grou
    -0.68
     Buses
    -0.68
     without
    -0.67
    او
    -0.66
    рик
    -0.65
    Transfer
    -0.63
    INAL
    -0.63
    POSITIVE LOGITS
    ancing
    0.80
    色が
    0.76
     creat
    0.73
     catalogues
    0.73
    accounts
    0.71
    blis
    0.71
    veston
    0.69
    cre
    0.69
     catalogs
    0.69
    boten
    0.68
    Activations Density 0.053%

    No Known Activations