© 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. 44639
    Prev
    Next
    INDEX
    Explanations

    relative clauses starting with which or who

    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
     아주
    0.49
    новой
    0.47
    ходя
    0.44
     उसको
    0.44
    ב
    0.43
    חי
    0.43
    দে
    0.43
    adı
    0.42
    然后
    0.41
    בן
    0.41
    POSITIVE LOGITS
    0.41
    ཎ
    0.39
     was
    0.39
     swim
    0.38
     hilly
    0.37
    我对
    0.37
     includes
    0.37
     पीड़
    0.37
     swamps
    0.37
     androidx
    0.36
    Activations Density 0.031%

    No Known Activations