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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12944
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -2.42
     probably
    -1.96
     which
    -1.89
     because
    -1.81
     the
    -1.81
     one
    -1.80
    っちゃった
    -1.72
     those
    -1.70
     really
    -1.70
     usually
    -1.68
    POSITIVE LOGITS
     모든
    1.60
     puder
    1.57
    ೩
    1.48
    푉
    1.48
     美丽
    1.48
    Когда
    1.47
    訁
    1.45
    诸多
    1.45
    Aantal
    1.44
     ทั้ง
    1.41
    Activations Density 0.001%

    No Known Activations