© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8330
    Prev
    Next
    INDEX
    Explanations

    adoption and application

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

    installation of modules, systems, and equipment

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     évaluations
    0.54
     சார்ப
    0.52
    谘
    0.52
    伟大
    0.51
     મત
    0.51
     अवज्ञा
    0.50
    शिंगटन
    0.50
     दिलच
    0.48
    閪
    0.48
    อะคาเดมี
    0.48
    POSITIVE LOGITS
     adopts
    0.70
    采用
    0.64
    安裝
    0.58
    安装
    0.57
     debugging
    0.56
    防水
    0.55
    施工
    0.54
     disinfection
    0.53
     小型
    0.53
     adopt
    0.53
    Activations Density 0.177%

    No Known Activations