© 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. 31-GEMMASCOPE-2-RES-65K
    7. 44747
    Prev
    Next
    INDEX
    Explanations

    converting to lowercase

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ₸
    0.51
     ਤੇ
    0.45
    ИС
    0.45
    高
    0.45
     उच्च
    0.44
    สูง
    0.43
     którym
    0.42
     высоких
    0.42
    噩
    0.42
    их
    0.41
    POSITIVE LOGITS
     matte
    0.46
    bene
    0.46
     disposer
    0.46
     search
    0.45
     lupus
    0.44
     Velvet
    0.44
     disposal
    0.44
     grapevine
    0.43
     keywords
    0.42
     feminist
    0.42
    Activations Density 0.078%

    No Known Activations