© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84817
    Prev
    Next
    INDEX
    Explanations

    boolean true

    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
      
    -2.66
     _________
    -2.61
     dando
    -2.44
     ???
    -2.42
     подходя
    -2.39
     L
    -2.38
     __________
    -2.38
    ↵↵
    -2.34
     is
    -2.33
     «
    -2.33
    POSITIVE LOGITS
    1
    2.98
     العالمي
    2.97
    橚
    2.89
     unquestionably
    2.89
     丁目
    2.81
     Harian
    2.73
    緜
    2.61
     Bahía
    2.55
    verride
    2.52
     キャンペーン
    2.52
    Activations Density 0.023%

    No Known Activations