© 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. 21748
    Prev
    Next
    INDEX
    Explanations

    Ah

    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
    卺
    -3.20
     ihre
    -2.88
    ſelf
    -2.86
    
    -2.69
    喈
    -2.63
     แต่
    -2.52
    ︲
    -2.42
     可愛い
    -2.38
    他们的
    -2.36
     唯美
    -2.34
    POSITIVE LOGITS
    {
    3.39
    [
    2.84
    For
    2.70
     Consequently
    2.64
     Lately
    2.61
    .
    2.61
     Officially
    2.53
     Unfortunately
    2.53
     Unlike
    2.45
     Essentially
    2.44
    Activations Density 0.002%

    No Known Activations