© 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. 42143
    Prev
    Next
    INDEX
    Explanations

    code imports and includes

    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
     rembourse
    -1.82
     probablement
    -1.79
     unſ
    -1.64
    ㈮
    -1.64
    当然
    -1.63
     passende
    -1.63
     美しい
    -1.62
    かなり
    -1.58
    Takk
    -1.55
    ㈬
    -1.54
    POSITIVE LOGITS
     two
    1.79
    begin
    1.78
     in
    1.73
     Wednesday
    1.70
    {
    1.70
     usually
    1.67
    -\
    1.66
     so
    1.65
     three
    1.64
     mostly
    1.64
    Activations Density 0.063%

    No Known Activations