© 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. 103910
    Prev
    Next
    INDEX
    Explanations

    durations and time units

    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
     statewide
    -0.86
     еже
    -0.78
    Pilot
    -0.77
     momentary
    -0.75
     momentarily
    -0.75
    鼾
    -0.75
     试
    -0.74
    Birch
    -0.71
     ounce
    -0.71
     wildfire
    -0.69
    POSITIVE LOGITS
     years
    1.71
     days
    1.69
     year
    1.45
     hours
    1.31
     months
    1.30
    days
    1.28
     month
    1.25
     Months
    1.16
     day
    1.10
     weeks
    1.09
    Activations Density 0.045%

    No Known Activations