© 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. 101988
    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
     revisor
    -1.84
     夜景
    -1.60
     shopee
    -1.59
    inės
    -1.58
     precin
    -1.55
    鄴
    -1.52
     torba
    -1.51
     Carrot
    -1.50
     lumpur
    -1.50
     食堂
    -1.49
    POSITIVE LOGITS
     to
    1.73
    </h4>
    1.73
     
    1.72
     "
    1.64
    .
    1.63
     "'
    1.59
    –
    1.52
     ("
    1.48
     “
    1.47
     etc
    1.46
    Activations Density 0.123%

    No Known Activations