© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49700
    Prev
    Next
    INDEX
    Explanations

    eternal life and immortality

    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
    prayer
    -0.81
    stě
    -0.81
    enservice
    -0.77
     sighed
    -0.77
     prayer
    -0.76
     whether
    -0.74
     pittura
    -0.73
    شكرا
    -0.72
     tempel
    -0.71
    setOrder
    -0.70
    POSITIVE LOGITS
     life
    2.17
     eternal
    1.84
     Life
    1.76
    Life
    1.68
     everlasting
    1.61
    eternal
    1.52
     LIFE
    1.52
    life
    1.49
     жизнь
    1.41
     immortality
    1.41
    Activations Density 0.009%

    No Known Activations