© 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. 48169
    Prev
    Next
    INDEX
    Explanations

    time zones and times

    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
    malige
    -1.52
     }^{
    -1.48
    稲田
    -1.41
    Þ
    -1.41
    bó
    -1.34
    gleiche
    -1.30
    Galactic
    -1.29
    ➩
    -1.29
     国道
    -1.29
     christ
    -1.29
    POSITIVE LOGITS
     that
    1.87
     then
    1.53
     are
    1.49
    するために
    1.42
    または
    1.42
     verfügt
    1.38
     have
    1.38
     påver
    1.32
    Then
    1.26
     víc
    1.26
    Activations Density 0.002%

    No Known Activations