© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105337
    Prev
    Next
    INDEX
    Explanations

    apostrophe followed by word

    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_10/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
     at
    -2.08
     reduce
    -1.97
     twelve
    -1.95
     their
    -1.95
     during
    -1.93
     eleven
    -1.93
     eight
    -1.78
     thirteen
    -1.77
     adding
    -1.75
     sixteen
    -1.75
    POSITIVE LOGITS
     '"
    2.81
     '-
    2.50
    -'
    2.39
     "'
    2.34
    ⎔
    2.33
     -'
    2.31
     '
    2.27
    /'
    2.22
    ⟣
    2.06
    
    2.05
    Activations Density 0.060%

    No Known Activations