© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47340
    Prev
    Next
    INDEX
    Explanations

    weather, host, Musk

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     그때
    0.43
     Allowing
    0.42
    বাজারে
    0.40
    Бі
    0.40
    ูก
    0.40
     Whoever
    0.39
     තම
    0.39
    بي
    0.39
    칼
    0.39
     Organization
    0.39
    POSITIVE LOGITS
    may
    0.37
    クト
    0.35
    oked
    0.35
     是否
    0.35
    anz
    0.35
    sak
    0.34
     medica
    0.34
    Ivy
    0.34
    ács
    0.34
    等方面
    0.34
    Activations Density 0.003%

    No Known Activations