© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109804
    Prev
    Next
    INDEX
    Explanations

    layout configuration

    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
    нент
    -0.90
    manteau
    -0.89
    땅
    -0.84
    uxx
    -0.77
     природы
    -0.76
    tijd
    -0.75
     tomó
    -0.74
    coleccion
    -0.73
    icherheit
    -0.72
     jezik
    -0.72
    POSITIVE LOGITS
     layout
    5.84
    layout
    4.53
     Layout
    4.44
    Layout
    3.98
     layouts
    3.94
     LAYOUT
    3.52
    布局
    3.50
     configuration
    3.41
    LAYOUT
    3.39
     arrangement
    3.28
    Activations Density 0.125%

    No Known Activations