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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93729
    Prev
    Next
    INDEX
    Explanations

    padding, margin, spacing, offset

    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
    uszka
    -0.91
    contentLoaded
    -0.89
    Kilder
    -0.86
    strtolower
    -0.85
     飾
    -0.83
    Når
    -0.80
    二十四
    -0.78
    〒
    -0.77
    iotti
    -0.77
     pass
    -0.75
    POSITIVE LOGITS
     margin
    2.02
     padding
    1.97
     spacing
    1.90
     offset
    1.79
    padding
    1.77
     gap
    1.74
     margins
    1.61
    Padding
    1.54
     Padding
    1.45
    margin
    1.42
    Activations Density 0.032%

    No Known Activations