© 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. 220143
    Prev
    Next
    INDEX
    Explanations

    reasonably apparent

    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
    喂
    0.45
     erop
    0.43
     vitaminas
    0.41
     settimane
    0.40
     reduziert
    0.40
     xong
    0.39
     ilg
    0.39
     weken
    0.38
     semanas
    0.38
     डीएनए
    0.37
    POSITIVE LOGITS
    crawl
    0.42
     দেবতা
    0.39
     Companion
    0.36
     отвер
    0.36
     Benedict
    0.35
    ぴ
    0.35
     companion
    0.34
    clidean
    0.34
     Burst
    0.34
     ባለ
    0.34
    Activations Density 0.002%

    No Known Activations