© 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. 99500
    Prev
    Next
    INDEX
    Explanations

    port and terminal facilities

    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
     then
    -1.51
    Ꭲ
    -1.28
     sorella
    -1.20
    　　“
    -1.19
     Maintenant
    -1.18
     sobremesa
    -1.16
     sopa
    -1.16
     damaligen
    -1.15
    ními
    -1.15
    もちろん
    -1.15
    POSITIVE LOGITS
    awn
    1.27
    ady
    1.18
    ading
    1.14
    ási
    1.14
     port
    1.13
     wie
    1.13
     seit
    1.13
     "
    1.11
    '"
    1.09
    mazaki
    1.08
    Activations Density 0.043%

    No Known Activations