© 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. 31-GEMMASCOPE-2-RES-262K
    7. 216054
    Prev
    Next
    INDEX
    Explanations

    Plastic Manufacturers

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

    AI, you, he

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    炵
    0.50
    atud
    0.47
    传感器
    0.47
     località
    0.46
     Sensors
    0.46
     بيانات
    0.46
    沃尔
    0.45
    涔
    0.45
    高级
    0.45
    了一個
    0.45
    POSITIVE LOGITS
     bullies
    0.51
    MMM
    0.47
     bullying
    0.46
     wipe
    0.44
     endot
    0.44
     invading
    0.44
    HERSHEY
    0.43
     interfacial
    0.43
     handbook
    0.42
     evolving
    0.42
    Activations Density 0.000%

    No Known Activations