© 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. 124728
    Prev
    Next
    INDEX
    Explanations

    app references

    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
    僰
    -2.69
    》，
    -2.45
    珰
    -2.34
     而
    -2.16
    驁
    -2.16
    ༀ
    -2.09
    きて
    -2.08
     オーバー
    -2.05
     promove
    -2.05
     administração
    -2.03
    POSITIVE LOGITS
    7
    2.98
    9
    2.97
    最初の
    2.78
    g
    2.73
    am
    2.70
    Ironically
    2.63
    p
    2.59
    begin
    2.50
    u
    2.47
    三个
    2.41
    Activations Density 0.031%

    No Known Activations