© 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. 114082
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
     while
    -2.00
     its
    -1.74
    ྄
    -1.67
    ladesh
    -1.51
     such
    -1.49
    
    -1.48
     out
    -1.48
     this
    -1.47
     atriz
    -1.41
     controladores
    -1.41
    POSITIVE LOGITS
     também
    1.76
     作り方
    1.68
     generali
    1.62
     Хотя
    1.57
     bahkan
    1.55
     mereka
    1.42
     вони
    1.42
    この記事
    1.41
    Kamera
    1.41
    今日も
    1.39
    Activations Density 0.026%

    No Known Activations