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. 117
    Prev
    Next
    INDEX
    Explanations

    context menu

    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
    炊き
    -0.83
    влений
    -0.78
    SneakyThrows
    -0.78
     giac
    -0.77
     indoors
    -0.77
     brinquedo
    -0.76
    maso
    -0.75
    ayas
    -0.75
    玉ねぎ
    -0.75
     जानकारी
    -0.74
    POSITIVE LOGITS
     context
    2.67
     menu
    2.53
    ContextMenu
    2.19
     Context
    2.19
     contextual
    2.11
    contextMenu
    2.08
    context
    2.06
     menus
    1.96
    menu
    1.91
     contexts
    1.84
    Activations Density 0.040%

    No Known Activations