© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15627
    Prev
    Next
    INDEX
    Explanations

    order

    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
    Negative Logits
    <bos>
    -2.00
    
    -1.73
    nicity
    -1.71
    眎
    -1.63
     únicas
    -1.62
    鲞
    -1.53
    而又
    -1.51
    ZED
    -1.48
     ἄ
    -1.47
     гораздо
    -1.47
    POSITIVE LOGITS
    瑧
    2.41
     order
    2.11
    谖
    2.00
    ramientas
    1.93
    焄
    1.93
    黻
    1.87
    
    1.84
    ين
    1.83
    Ако
    1.80
    خخ
    1.80
    Activations Density 0.050%

    No Known Activations