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. 41
    Prev
    Next
    INDEX
    Explanations

    spacing and layout

    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
    ราะ
    -0.93
    BufferSize
    -0.85
     stockholders
    -0.85
     complémentaires
    -0.84
     körül
    -0.84
     reins
    -0.79
    tető
    -0.77
    ansons
    -0.77
    ynchronously
    -0.76
    gridad
    -0.76
    POSITIVE LOGITS
     spacers
    0.98
     layouts
    0.97
     layout
    0.97
     Distribute
    0.91
     spaces
    0.88
     tallest
    0.86
    スペース
    0.85
     Spacing
    0.85
     space
    0.84
     espacios
    0.84
    Activations Density 0.007%

    No Known Activations