© 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. 229485
    Prev
    Next
    INDEX
    Explanations

    transactionspaymentsellingbookstoresapp

    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
    霧
    0.49
    ఫ్
    0.47
    т
    0.47
    нія
    0.47
    annten
    0.46
     воды
    0.46
    俵
    0.46
    盧
    0.45
    лган
    0.45
    მასრულ
    0.45
    POSITIVE LOGITS
     e
    0.45
     eBook
    0.43
     Católica
    0.41
     वरिष्ठ
    0.41
     di
    0.40
    ……………………
    0.40
     bookstores
    0.40
     SITE
    0.39
     £
    0.39
     분
    0.39
    Activations Density 0.000%

    No Known Activations