© 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. 72082
    Prev
    Next
    INDEX
    Explanations

    system configuration settings

    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
    もの
    -1.98
    眎
    -1.80
    眼睛
    -1.71
     navires
    -1.70
    </i>
    -1.69
     特写
    -1.66
    修正
    -1.65
    s
    -1.64
     Tasks
    -1.63
     剧照
    -1.63
    POSITIVE LOGITS
    廰
    2.11
    嵎
    1.91
    户外
    1.91
    耜
    1.89
    
    1.88
    要用
    1.84
    贔
    1.83
    谞
    1.83
    Зно
    1.81
    IonicModule
    1.80
    Activations Density 0.013%

    No Known Activations