© 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. 10-GEMMASCOPE-RES-131K
    7. 47683
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    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
     они
    -1.95
     or
    -1.90
     how
    -1.84
     In
    -1.75
     increase
    -1.70
     Some
    -1.70
     which
    -1.69
     Of
    -1.63
     improve
    -1.57
     или
    -1.56
    POSITIVE LOGITS
     keramik
    1.59
     OGSÅ
    1.58
    蓠
    1.55
     alun
    1.54
    both
    1.52
    atürk
    1.49
     pakan
    1.48
     lampa
    1.48
     sapiens
    1.48
    lève
    1.43
    Activations Density 0.027%

    No Known Activations