© 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. 1709
    Prev
    Next
    INDEX
    Explanations

    information and technology concepts

    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
     which
    -1.77
     που
    -1.56
     October
    -1.51
     February
    -1.49
    чностью
    -1.45
     创建时间
    -1.43
     those
    -1.42
    νει
    -1.38
    ｪ
    -1.38
     janvier
    -1.34
    POSITIVE LOGITS
    ed
    1.34
     entsprechenden
    1.33
    se
    1.31
    がっ
    1.31
    According
    1.30
    con
    1.28
    sup
    1.25
    begin
    1.25
     reign
    1.23
    它的
    1.22
    Activations Density 1.142%

    No Known Activations