© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23750
    Prev
    Next
    INDEX
    Explanations

    how long something lasts

    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
    нах
    -0.88
    теров
    -0.84
    ainte
    -0.74
     expo
    -0.73
     univ
    -0.73
    SQLException
    -0.71
    Xem
    -0.71
    ό
    -0.71
    license
    -0.71
     снимки
    -0.70
    POSITIVE LOGITS
     lasts
    5.47
     lasted
    5.19
     last
    4.19
     lasting
    3.59
    lasts
    3.48
    Last
    2.75
    lasting
    2.70
    last
    2.70
     Last
    2.67
     LAST
    2.56
    Activations Density 0.065%

    No Known Activations