© 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. 68379
    Prev
    Next
    INDEX
    Explanations

    Saturday Night Live

    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
    皷
    -1.90
    氿
    -1.86
     但是
    -1.73
    ла
    -1.66
    od
    -1.64
    啻
    -1.62
     السيارة
    -1.61
    anyeol
    -1.60
    姈
    -1.57
     ไม่มี
    -1.55
    POSITIVE LOGITS
    呖
    2.36
    ஂ
    2.28
    вгений
    1.99
     specialmente
    1.91
    嗵
    1.90
    ｲ
    1.89
    　↓
    1.86
    ⽩
    1.86
    ']
    1.80
    写真は
    1.78
    Activations Density 0.002%

    No Known Activations