© 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. 34-GEMMASCOPE-RES-131K
    7. 90835
    Prev
    Next
    INDEX
    Explanations

    refresher course or review

    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_34/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
     remplacer
    -0.90
     transformación
    -0.83
    -0.81
    ubah
    -0.79
    radora
    -0.78
    QO
    -0.77
     Rowe
    -0.77
    inker
    -0.76
     Ис
    -0.74
    
    -0.74
    POSITIVE LOGITS
     refresher
    4.25
     refresh
    3.86
    refresh
    3.14
     refreshing
    2.97
     Refresh
    2.88
    Refresh
    2.77
     recap
    2.75
     refres
    2.69
     review
    2.66
     refreshed
    2.63
    Activations Density 0.074%

    No Known Activations