© 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. 34-GEMMASCOPE-RES-131K
    7. 45744
    Prev
    Next
    INDEX
    Explanations

    dates and months

    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_34/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
    July
    -2.42
    June
    -2.33
     July
    -2.27
     summer
    -2.20
     June
    -2.19
     JUNE
    -2.06
    Summer
    -2.05
    JUNE
    -2.03
    summer
    -2.03
     SUMMER
    -2.00
    POSITIVE LOGITS
     January
    4.47
    January
    3.97
     February
    3.80
    February
    3.53
     Feb
    3.44
     janvier
    3.17
     january
    3.08
     JANUARY
    3.06
    JANUARY
    2.98
     winter
    2.94
    Activations Density 0.452%

    No Known Activations