© 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. 110644
    Prev
    Next
    INDEX
    Explanations

    sprinkle and sprinkler usage

    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
     Careful
    -2.98
    {
    -2.88
    as
    -2.69
    ⢪
    -2.63
    瓩
    -2.55
    The
    -2.52
     safest
    -2.52
    ჻
    -2.50
     eigenen
    -2.44
    女兒
    -2.44
    POSITIVE LOGITS
    鈇
    3.33
    
    2.95
     ſame
    2.95
    vantaged
    2.81
    趼
    2.75
    鴣
    2.72
    鱨
    2.64
    珰
    2.64
    垕
    2.64
     unſ
    2.63
    Activations Density 0.003%

    No Known Activations