© 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. 22-GEMMASCOPE-RES-131K
    7. 80040
    Prev
    Next
    INDEX
    Explanations

    time and duration

    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_22/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
    glected
    -1.06
    nių
    -1.05
    も
    -1.03
     arī
    -1.00
    asive
    -0.97
    appé
    -0.94
    杀手
    -0.92
    ſing
    -0.91
     garantía
    -0.90
     ENTRY
    -0.90
    POSITIVE LOGITS
     regarding
    1.13
     Decken
    1.05
     başlad
    0.96
    Approximately
    0.94
     both
    0.91
     NACIONAL
    0.91
     Maschinen
    0.90
     gâteau
    0.90
     Konzer
    0.89
    beleid
    0.89
    Activations Density 0.068%

    No Known Activations