© 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. 119716
    Prev
    Next
    INDEX
    Explanations

    a place, little extra, comparable sales

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

    units of time

    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
     इंटीग्र
    0.48
     Objectives
    0.46
     legger
    0.46
     Кара
    0.45
                 
    0.45
     учащихся
    0.45
     победи
    0.43
     विजे
    0.43
     डर
    0.43
     обучения
    0.42
    POSITIVE LOGITS
    단
    0.54
     회사
    0.51
     hàng
    0.49
    マンション
    0.48
    াস্থ্য
    0.46
    ROOM
    0.45
    (',')
    0.43
    (",")
    0.43
    in
    0.43
    čně
    0.42
    Activations Density 0.000%

    No Known Activations