© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70275
    Prev
    Next
    INDEX
    Explanations

    European countries, standards, commissioner, record, birth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gezogen
    -2.09
     プレート
    -2.06
     is
    -2.05
     può
    -2.00
     ジップ
    -1.99
     
    -1.97
    比如说
    -1.95
     VERY
    -1.91
    gestellten
    -1.91
     küche
    -1.90
    POSITIVE LOGITS
     вещь
    2.14
     exquisite
    2.13
    瑧
    2.11
     飲
    2.11
    ઁ
    2.05
     multifaceted
    2.02
    m
    2.00
    ve
    1.99
    呖
    1.99
     мужская
    1.98
    Activations Density 0.027%

    No Known Activations