© 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. 41-GEMMASCOPE-2-RES-262K
    7. 35305
    Prev
    Next
    INDEX
    Explanations

    containers and empty shells

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Knee
    0.45
    gherita
    0.44
    淢
    0.42
    ktionen
    0.40
    섦
    0.40
     teorema
    0.40
    írez
    0.39
    Chord
    0.39
    仴
    0.38
     Curriculum
    0.38
    POSITIVE LOGITS
    容器
    2.19
     containers
    2.11
     container
    2.08
     контей
    1.93
    container
    1.90
     Containers
    1.87
    containers
    1.80
    Containers
    1.77
    Container
    1.74
     Container
    1.74
    Activations Density 0.004%

    No Known Activations