© 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. 10058
    Prev
    Next
    INDEX
    Explanations

    Geek or Sukhoi

    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
    ཫ
    -3.09
    摃
    -2.72
    偸
    -2.67
    掼
    -2.66
    ཥ
    -2.64
    嫫
    -2.64
    壜
    -2.59
    魨
    -2.56
    鲀
    -2.52
    哙
    -2.47
    POSITIVE LOGITS
    [
    2.88
    ed
    2.64
    {
    2.63
    or
    2.45
    #
    2.42
    ৪
    2.38
    ↵↵
    2.33
    www
    2.27
    .
    2.23
    ar
    2.19
    Activations Density 0.005%

    No Known Activations