© 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. 104571
    Prev
    Next
    INDEX
    Explanations

    mathematical theory and concepts

    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
     fantastic
    -1.71
    搋
    -1.54
    primarily
    -1.53
     AMAZING
    -1.49
    
    -1.45
     terrific
    -1.45
     spectacular
    -1.41
     grumbled
    -1.41
     astonishing
    -1.41
     marvelous
    -1.41
    POSITIVE LOGITS
     that
    2.17
     Because
    1.77
     this
    1.65
     Since
    1.64
     not
    1.64
     would
    1.64
     During
    1.63
     Despite
    1.61
     Being
    1.61
     becomes
    1.61
    Activations Density 0.183%

    No Known Activations