© 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. 68872
    Prev
    Next
    INDEX
    Explanations

    events and gatherings

    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
     for
    -1.25
     to
    -1.15
    futbolista
    -1.04
     ognuno
    -1.02
     einst
    -1.01
     in
    -0.99
     after
    -0.98
     at
    -0.96
     добраться
    -0.93
    yaç
    -0.93
    POSITIVE LOGITS
     such
    1.25
     крупных
    1.13
     fermée
    1.09
     Beschluss
    1.09
     etc
    1.07
    Whenever
    1.05
     récemment
    1.00
     occasions
    0.99
     Всё
    0.99
    <0xCE>
    0.98
    Activations Density 0.050%

    No Known Activations