© 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. 68476
    Prev
    Next
    INDEX
    Explanations

    before courts and judges

    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
    which
    -1.81
    来不及
    -1.78
    .
    -1.69
    ıyorum
    -1.65
     $
    -1.61
     ambayo
    -1.55
    ],
    -1.53
     jego
    -1.51
    上次
    -1.46
     indicando
    -1.43
    POSITIVE LOGITS
    喾
    2.22
     They
    1.91
     vittoria
    1.89
    ቍ
    1.88
     вона
    1.88
    
    1.87
    ﹍﹍
    1.86
     you
    1.83
     сказал
    1.77
     gustado
    1.75
    Activations Density 0.016%

    No Known Activations