© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2861
    Prev
    Next
    INDEX
    Explanations

    annual compounding periods

    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_40_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
     díky
    0.46
     rů
    0.46
     ശിഷ്യ
    0.46
     پیپلز
    0.45
    ăz
    0.45
    知名
    0.44
    THIRD
    0.44
    蜢
    0.44
    恸
    0.43
    䏹
    0.43
    POSITIVE LOGITS
     yearly
    0.64
     periods
    0.63
     annual
    0.60
    periods
    0.59
     annually
    0.58
     Yearly
    0.54
     period
    0.54
     one
    0.52
     times
    0.52
     implied
    0.52
    Activations Density 0.001%

    No Known Activations