© 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. 102360
    Prev
    Next
    INDEX
    Explanations

    numbers and dollar amounts

    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
     到着
    -1.83
     which
    -1.79
     料金
    -1.67
     increased
    -1.63
     how
    -1.60
    より
    -1.57
     также
    -1.57
     increase
    -1.55
     increases
    -1.49
     new
    -1.48
    POSITIVE LOGITS
     into
    1.87
    ︲
    1.48
    í
    1.41
    HttpFoundation
    1.40
    𓐍
    1.39
     them
    1.38
     ()
    1.38
    癭
    1.37
    𝑝
    1.36
    assium
    1.35
    Activations Density 0.048%

    No Known Activations