© 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. 19159
    Prev
    Next
    INDEX
    Explanations

    pedagogy and teaching

    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
     включая
    -2.28
    '
    -2.25
     Of
    -1.90
    哔
    -1.89
    -1.82
    -1.80
    i
    -1.76
     что
    -1.72
    ins
    -1.68
    ์
    -1.67
    POSITIVE LOGITS
     theses
    2.02
     vollständige
    2.00
    .
    1.98
     "")
    1.86
     Daß
    1.80
     Akhir
    1.79
     используют
    1.76
    :”
    1.75
     Tujuan
    1.75
     october
    1.75
    Activations Density 0.003%

    No Known Activations