© 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. 47920
    Prev
    Next
    INDEX
    Explanations

    date picker and formats

    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
     dates
    -1.02
     Dates
    -1.01
    Dates
    -0.90
    DateRange
    -0.85
    dates
    -0.82
     DATES
    -0.81
     kro
    -0.81
    стная
    -0.80
     ново
    -0.79
     komp
    -0.77
    POSITIVE LOGITS
     time
    1.16
    time
    1.09
     format
    1.00
    picker
    0.95
    format
    0.93
    FORMAT
    0.90
    Picker
    0.88
    fmt
    0.88
     formatting
    0.86
     formats
    0.85
    Activations Density 0.035%

    No Known Activations