© 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. 68969
    Prev
    Next
    INDEX
    Explanations

    recently or currently

    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
    decade
    -1.19
     década
    -1.16
     decades
    -1.13
     cokelat
    -1.09
     habían
    -1.09
     никогда
    -1.05
     tuo
    -1.03
     postales
    -1.02
    ゙
    -1.01
     YEARS
    -0.96
    POSITIVE LOGITS
     today
    2.50
     recently
    2.47
     now
    2.14
     currently
    2.08
     сейчас
    1.91
    到现在
    1.88
    現在は
    1.87
     aujourd
    1.84
     현재
    1.80
     yesterday
    1.78
    Activations Density 0.096%

    No Known Activations