© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 160393
    Prev
    Next
    INDEX
    Explanations

    scheduling and checking out

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

    no god but God

    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
    Not in Any Lists

    No Comments

    Negative Logits
    错误
    0.54
     venden
    0.52
     miesią
    0.50
     Vendor
    0.47
    eden
    0.45
    Vendor
    0.45
     方
    0.45
     kesalahan
    0.45
     بتاريخ
    0.45
     ORD
    0.45
    POSITIVE LOGITS
    輔
    0.46
    軛
    0.46
    場面
    0.45
     levers
    0.40
     Gagn
    0.40
     চক্রবর্তী
    0.39
     листо
    0.38
     crock
    0.38
     dirig
    0.38
     Havre
    0.38
    Activations Density 0.001%

    No Known Activations