© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192965
    Prev
    Next
    INDEX
    Explanations

    ornate embellished peony exquisite emerald

    np_acts-logits-general · gemini-2.5-flash-lite

    economic shifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    놔
    0.56
    }(\
    0.51
    อน
    0.50
    вел
    0.48
    現在
    0.47
    ดี๋ยว
    0.47
    wayat
    0.47
    โค
    0.47
    ід
    0.46
    🕝
    0.46
    POSITIVE LOGITS
     peony
    0.55
     exquisite
    0.54
     spacers
    0.54
     Màu
    0.53
     Uma
    0.52
     emerald
    0.52
     ornamented
    0.52
     peonies
    0.51
     ornate
    0.49
     embellished
    0.48
    Activations Density 0.001%

    No Known Activations