© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99284
    Prev
    Next
    INDEX
    Explanations

    director or author names

    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_34/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
     設計
    -1.02
    】:
    -0.96
     fracas
    -0.94
     雙
    -0.94
     遊戲
    -0.93
     caric
    -0.90
     hacerlo
    -0.90
    Unders
    -0.89
    äsident
    -0.88
    FURTHER
    -0.88
    POSITIVE LOGITS
     the
    0.96
     выше
    0.77
              
    0.76
     arī
    0.75
     Feuchtigkeit
    0.75
    ^{-}
    0.73
     stolen
    0.73
     yaitu
    0.73
     spielen
    0.73
     brighter
    0.71
    Activations Density 0.108%

    No Known Activations