© 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. 73777
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    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
    🍀
    -0.99
     foton
    -0.98
     postale
    -0.98
    たとえば
    -0.96
     Gratis
    -0.95
     deklar
    -0.93
    ☘
    -0.92
    慑
    -0.91
    //'
    -0.91
     istor
    -0.91
    POSITIVE LOGITS
     then
    1.25
     final
    1.20
     which
    1.11
     nuovamente
    1.09
     wiederum
    1.02
     Wohnen
    1.02
     again
    0.99
     wieder
    0.96
     it
    0.93
     results
    0.92
    Activations Density 0.033%

    No Known Activations