© 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. 10-GEMMASCOPE-RES-131K
    7. 103586
    Prev
    Next
    INDEX
    Explanations

    lifelong or lifespan phenomena

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

    The neuron primarily activates for the term "lifelong" or variations like "life-long", particularly when describing enduring conditions, pursuits, or characteristics.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     We
    -2.66
     When
    -2.42
    戆
    -2.41
     
    -2.30
    抬手
    -2.28
    ↵
    -2.28
    蟥
    -2.28
    戽
    -2.17
    低声
    -2.13
    釭
    -2.11
    POSITIVE LOGITS
    s
    2.80
    u
    2.78
    的
    2.67
    ?"
    2.50
    ‪.‬‬
    2.50
    ；
    2.48
    是
    2.48
    3
    2.42
    8
    2.42
     stehe
    2.41
    Activations Density 0.003%

    No Known Activations