© 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. 90699
    Prev
    Next
    INDEX
    Explanations

    life followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on the word "life" especially when it appears in scientific contexts like "life cycle," "life span," or "life course."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily detects the word “life,” especially when it appears as a standalone term or in compounds like life‐cycle, lifespan, or life‐course.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     life
    -2.00
    life
    -1.33
    Life
    -1.30
    LIFE
    -1.26
    人生
    -1.16
     жизни
    -1.13
     Life
    -1.05
     LIFE
    -1.01
     زندگی
    -1.00
    ife
    -0.99
    POSITIVE LOGITS
    hist
    0.87
     sciences
    0.84
     Science
    0.82
     science
    0.80
     Diese
    0.80
     besonders
    0.79
     stolet
    0.79
     vital
    0.77
    SCI
    0.76
    五六
    0.76
    Activations Density 0.029%

    No Known Activations