© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53484
    Prev
    Next
    INDEX
    Explanations

    duration in years ending now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    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
     decades
    0.74
     décadas
    0.60
    Years
    0.55
     years
    0.53
     Jahrze
    0.52
    years
    0.50
     वर्षों
    0.49
    ো
    0.49
    ע
    0.48
     década
    0.47
    POSITIVE LOGITS
     இதுவரை
    0.56
     sekarang
    0.54
     сейчас
    0.54
     หนึ่ง
    0.53
     오늘은
    0.53
     mittlerweile
    0.52
    ตอนนี้
    0.52
     Currently
    0.51
     सध्या
    0.51
     현재
    0.49
    Activations Density 0.008%

    No Known Activations