© 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-16K
    7. 573
    Prev
    Next
    INDEX
    Explanations

    describing lists of items

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Nevertheless
    0.39
     maaaring
    0.38
     demek
    0.35
     ataupun
    0.35
     nevertheless
    0.34
     বলার
    0.34
     derfor
    0.34
     categorization
    0.34
     rusak
    0.33
    😐
    0.33
    POSITIVE LOGITS
    ала
    0.34
     รับ
    0.33
     Ready
    0.33
     работа
    0.33
    теше
    0.33
     thúc
    0.33
     оптими
    0.33
     trabaja
    0.32
     Comenz
    0.32
     рабо
    0.32
    Activations Density 0.953%

    No Known Activations