© 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. 72090
    Prev
    Next
    INDEX
    Explanations

    QtGui, UIKit, maps, bigint, BITMAP, 文档

    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
    銲
    -3.08
    🧌
    -2.92
    
    -2.72
     新款
    -2.69
     domini
    -2.63
     marcos
    -2.58
     polie
    -2.58
    闿
    -2.56
     palio
    -2.53
     paradigma
    -2.53
    POSITIVE LOGITS
    1
    3.09
    8
    3.00
    聳
    2.77
    9
    2.63
    可以
    2.63
    是非常
    2.58
     We
    2.50
    6
    2.50
        
    2.45
    3
    2.45
    Activations Density 0.002%

    No Known Activations