© 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. 83922
    Prev
    Next
    INDEX
    Explanations

    years, duration, and tenure

    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
     visitar
    -0.85
     الظ
    -0.77
    луй
    -0.75
    lanan
    -0.75
    пление
    -0.73
     速
    -0.73
     Ryzen
    -0.72
    romptu
    -0.71
    Weekly
    -0.71
    ynchronous
    -0.69
    POSITIVE LOGITS
     years
    3.06
     seniority
    2.69
     tenure
    2.52
     Years
    2.17
     longevity
    2.05
     length
    2.03
    years
    1.98
    Years
    1.88
     duration
    1.80
     YEARS
    1.80
    Activations Density 0.059%

    No Known Activations