© 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. 52768
    Prev
    Next
    INDEX
    Explanations

    stewardship and trusteeship

    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
     advisory
    0.44
    ೆಂ
    0.43
    ক্ষিপ্ত
    0.42
     خطر
    0.41
     adlı
    0.39
     पीड़ित
    0.39
     coyote
    0.38
    رآ
    0.37
    嵓
    0.36
     こ
    0.36
    POSITIVE LOGITS
     entrusted
    0.48
     entrust
    0.47
    AMM
    0.42
     servant
    0.42
    ACCT
    0.38
     servants
    0.38
     талант
    0.37
    管理
    0.37
    osomal
    0.37
     SERV
    0.36
    Activations Density 0.006%

    No Known Activations