© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20005
    Prev
    Next
    INDEX
    Explanations

    explaining a context or situation

    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
    ！"
    -3.50
    蟊
    -3.11
     kommende
    -2.83
    簟
    -2.78
     occhiali
    -2.77
    ugeot
    -2.77
     orologio
    -2.75
    炱
    -2.75
    鶲
    -2.75
     scattata
    -2.73
    POSITIVE LOGITS
    .
    4.69
     \
    2.69
     l
    2.58
    (
    2.42
     To
    2.42
     Then
    2.41
    ),
    2.39
     e
    2.39
     
    2.39
     zahlreichen
    2.38
    Activations Density 0.011%

    No Known Activations