© 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. 130195
    Prev
    Next
    INDEX
    Explanations

    borrowing and transliterations

    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
    Negative Logits
    Rural
    0.40
     implication
    0.39
    Baseline
    0.37
     rural
    0.36
    peach
    0.36
    CBC
    0.36
     Rural
    0.35
    Rud
    0.35
    신
    0.35
     baseline
    0.34
    POSITIVE LOGITS
     borrowing
    1.05
     borrowings
    1.05
     borrow
    0.96
     borrowed
    0.95
     Borrow
    0.94
    借
    0.92
    borrow
    0.89
    Borrow
    0.89
     borrows
    0.86
     loan
    0.80
    Activations Density 0.079%

    No Known Activations