© 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. 22-GEMMASCOPE-RES-131K
    7. 64328
    Prev
    Next
    INDEX
    Explanations

    references or sources

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    などの
    -1.20
    ​​​
    -0.92
    kuit
    -0.91
    eens
    -0.87
    mathrm
    -0.86
     opção
    -0.85
    :"-
    -0.85
    ：……
    -0.84
     these
    -0.84
    tect
    -0.83
    POSITIVE LOGITS
    ・・・・・・・・
    1.12
     ministra
    0.97
    Недостатки
    0.96
    Forrás
    0.95
    ＝＝＝＝
    0.94
     balón
    0.93
    Referințe
    0.91
     péro
    0.90
     chapéu
    0.89
    Источник
    0.88
    Activations Density 0.047%

    No Known Activations