© 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. 146751
    Prev
    Next
    INDEX
    Explanations

    regulations, authorization, conditions, score

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

    ailments and conditions

    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
    拍卖
    0.52
    的新
    0.50
    বাজার
    0.46
     новой
    0.46
     เรือ
    0.46
    收购
    0.46
    了很多
    0.46
    卖
    0.45
     financiero
    0.45
    鐟
    0.45
    POSITIVE LOGITS
     aliments
    0.57
     regimens
    0.57
     illness
    0.56
     anormal
    0.55
     illnesses
    0.54
     maladie
    0.52
     harmless
    0.51
     dosages
    0.51
     afflict
    0.49
     sympt
    0.49
    Activations Density 0.000%

    No Known Activations