© 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. 34-GEMMASCOPE-RES-131K
    7. 76399
    Prev
    Next
    INDEX
    Explanations

    entity named

    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
     şun
    -0.93
    INCLUDING
    -0.92
     unabhäng
    -0.91
    鍍
    -0.89
     künftig
    -0.87
    nó
    -0.86
     Including
    -0.85
     ešte
    -0.85
    에는
    -0.82
     zwłaszcza
    -0.82
    POSITIVE LOGITS
     named
    6.91
    named
    4.97
    Named
    4.28
     Named
    3.98
     bernama
    3.88
     name
    3.77
     namens
    3.72
     tên
    3.33
    ชื่อ
    3.17
    名叫
    3.09
    Activations Density 0.105%

    No Known Activations