© 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. 41511
    Prev
    Next
    INDEX
    Explanations

    involvement of

    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
    ##
    -1.51
    骝
    -1.48
    。
    -1.40
     meisten
    -1.39
    緜
    -1.38
     rood
    -1.34
     intorno
    -1.34
    Ⓡ
    -1.33
     ,
    -1.32
    変換
    -1.32
    POSITIVE LOGITS
    {
    1.87
    8
    1.59
    你也
    1.54
    她也
    1.52
    5
    1.52
     quatro
    1.48
     tada
    1.45
    junctive
    1.42
     +
    1.41
     people
    1.38
    Activations Density 0.049%

    No Known Activations