© 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. 11378
    Prev
    Next
    INDEX
    Explanations

    clear quality

    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
     try
    -1.91
     be
    -1.80
     können
    -1.73
    皷
    -1.69
     kunnen
    -1.66
     десять
    -1.63
     tutte
    -1.52
     mismo
    -1.48
     momentous
    -1.47
    <i>
    -1.46
    POSITIVE LOGITS
    ៚
    1.75
     This
    1.64
     srl
    1.59
     ITALY
    1.56
    こちらが
    1.56
     Inggris
    1.55
     clear
    1.54
    。”
    1.53
    ężczy
    1.52
     naudoti
    1.52
    Activations Density 0.032%

    No Known Activations