© 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. 235484
    Prev
    Next
    INDEX
    Explanations

    licensed by

    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
    ס
    0.47
     设置
    0.47
    ITECT
    0.46
     weir
    0.45
     কন্যার
    0.44
    two
    0.44
    ೧
    0.43
    ্রী
    0.43
    daughter
    0.43
    findElement
    0.43
    POSITIVE LOGITS
     stade
    0.50
     Merchandise
    0.47
     resolute
    0.44
    нең
    0.44
    рити
    0.44
    fas
    0.43
    uous
    0.43
    どこ
    0.43
    私
    0.43
     இடைய
    0.42
    Activations Density 0.000%

    No Known Activations