© 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. 9626
    Prev
    Next
    INDEX
    Explanations

    past time references

    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
     today
    -1.87
     here
    -1.51
    aujourd
    -1.45
     attualmente
    -1.45
    现在的
    -1.37
     huidige
    -1.21
     aujourd
    -1.19
    怎麼辦
    -1.18
     heute
    -1.18
     currently
    -1.18
    POSITIVE LOGITS
     had
    2.36
     había
    2.08
     previous
    2.06
     habían
    2.05
     earlier
    2.05
     предыду
    1.81
     anteriores
    1.76
     prior
    1.73
     sebelumnya
    1.73
     zuvor
    1.65
    Activations Density 0.100%

    No Known Activations