© 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. 29081
    Prev
    Next
    INDEX
    Explanations

    boxing and boxers

    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
     is
    -2.61
    welling
    -2.59
     歳
    -2.55
    AutoresizingMask
    -2.44
     fungerar
    -2.30
    梣
    -2.27
    '
    -2.20
    苼
    -2.19
    ("");
    -2.17
    ("-
    -2.17
    POSITIVE LOGITS
    皷
    2.95
     vielfäl
    2.81
     gän
    2.70
     kontinuier
    2.63
     beinahe
    2.61
     speziellen
    2.52
     wiederhol
    2.50
    㐂
    2.48
    劼
    2.48
    imantan
    2.48
    Activations Density 0.004%

    No Known Activations