© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31442
    Prev
    Next
    INDEX
    Explanations

    lifespan or longevity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jeunes
    0.55
    젊
    0.54
     jóvenes
    0.50
     joven
    0.49
     젊
    0.48
     jeune
    0.47
     jovens
    0.46
    young
    0.46
     trẻ
    0.45
     jovem
    0.44
    POSITIVE LOGITS
     lifelong
    0.40
     lifetime
    0.38
     lifespan
    0.37
    生涯
    0.35
     life
    0.34
     lifecycle
    0.34
     Potomac
    0.34
    瓠
    0.33
     জন্ত
    0.33
     GAR
    0.33
    Activations Density 0.014%

    No Known Activations