© 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-65K
    7. 1760
    Prev
    Next
    INDEX
    Explanations

    multi-language terms

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sear
    0.27
     thro
    0.27
    ifferentiated
    0.26
     epidermal
    0.26
     mucosal
    0.26
    ithe
    0.26
     columnalign
    0.26
    hesis
    0.25
    agonal
    0.24
    _
    0.24
    POSITIVE LOGITS
     newbies
    0.29
     experiencias
    0.29
     모든
    0.29
     trông
    0.29
    เริ่ม
    0.28
     चुने
    0.27
     количеством
    0.27
     좋은
    0.27
     wybra
    0.27
     buyers
    0.26
    Activations Density 3.827%

    No Known Activations