© 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. 72199
    Prev
    Next
    INDEX
    Explanations

    words of titles

    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
                    
    -2.22
    ↵
    -2.02
    这么多
    -1.86
    閙
    -1.81
     deixando
    -1.77
    ETHOD
    -1.70
     behalten
    -1.68
     \
    -1.67
     schließen
    -1.66
    i
    -1.64
    POSITIVE LOGITS
     '?
    1.95
    蓐
    1.71
    鞴
    1.70
     内衣
    1.68
    人們
    1.65
    ｙ
    1.65
    💧
    1.62
    我們
    1.61
     Belakang
    1.59
    ❕
    1.59
    Activations Density 0.016%

    No Known Activations