© 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. 192523
    Prev
    Next
    INDEX
    Explanations

    interact with, finished, preceded by

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

    user prompts and requests

    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
     সাথে
    0.47
    뒷
    0.45
     শিখে
    0.44
    ğin
    0.44
    :=\
    0.44
    richTextBox
    0.43
     Seah
    0.43
     giov
    0.42
     Attach
    0.42
     फुलकारी
    0.41
    POSITIVE LOGITS
     цель
    0.48
    падает
    0.47
    》
    0.46
    agé
    0.45
     to
    0.45
     workflows
    0.45
     upped
    0.44
     kernels
    0.44
     caveats
    0.44
     seks
    0.44
    Activations Density 0.002%

    No Known Activations