© 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. 157
    Prev
    Next
    INDEX
    Explanations

    make up for

    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
     two
    -1.81
     new
    -1.73
     provocó
    -1.59
     people
    -1.52
    佯
    -1.51
     mantiene
    -1.48
     aparentemente
    -1.48
     four
    -1.47
     ayudó
    -1.45
     saját
    -1.45
    POSITIVE LOGITS
    kelijk
    1.51
    ässä
    1.45
    呖
    1.43
     Giugno
    1.42
     insufficiency
    1.40
    inės
    1.39
    ningar
    1.39
    ätta
    1.38
    anego
    1.38
    fielder
    1.37
    Activations Density 0.022%

    No Known Activations