© 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. 103861
    Prev
    Next
    INDEX
    Explanations

    duration in 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
     decade
    -0.99
     Decade
    -0.93
     years
    -0.91
     دهه
    -0.88
     década
    -0.87
     week
    -0.86
    多年的
    -0.81
    十年
    -0.80
     decades
    -0.79
     day
    -0.78
    POSITIVE LOGITS
     months
    3.56
     six
    2.95
    半年
    2.80
    Months
    2.36
    months
    2.34
    six
    2.28
     Months
    2.27
    几个月
    2.22
     maanden
    1.97
     meses
    1.85
    Activations Density 0.139%

    No Known Activations