© 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. 31595
    Prev
    Next
    INDEX
    Explanations

    adjective-noun phrases

    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
    ძლი
    0.50
    ש
    0.49
    اقی
    0.47
    ر
    0.47
    ം
    0.46
    عمل
    0.45
    ский
    0.45
    üche
    0.45
    স
    0.45
    ToWrite
    0.44
    POSITIVE LOGITS
     alarma
    0.50
     tratar
    0.48
     echocardi
    0.46
    ப்பட்ட
    0.45
     filet
    0.45
     alk
    0.44
     terk
    0.44
     dese
    0.43
     puff
    0.43
     planks
    0.43
    Activations Density 0.005%

    No Known Activations