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. 8402
    Prev
    Next
    INDEX
    Explanations

    file names and basenames

    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
     whereabouts
    -0.78
    innig
    -0.77
     anderen
    -0.72
    vap
    -0.72
    tych
    -0.71
    getDescriptor
    -0.70
    gor
    -0.69
    gräns
    -0.69
    loren
    -0.69
    liess
    -0.68
    POSITIVE LOGITS
     basename
    2.48
    basename
    2.39
     name
    1.63
    文件名
    1.47
     getName
    1.43
     filename
    1.38
     Bas
    1.26
    name
    1.23
    NAME
    1.20
    getName
    1.19
    Activations Density 0.027%

    No Known Activations