© 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. 86784
    Prev
    Next
    INDEX
    Explanations

    legal citations and proper 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
     gola
    -0.90
    делки
    -0.85
     or
    -0.81
    正式
    -0.81
    кля
    -0.79
    ׄ
    -0.77
     дописа
    -0.76
     until
    -0.75
     kitab
    -0.74
    beheer
    -0.73
    POSITIVE LOGITS
     doctrina
    1.09
     critici
    0.94
     وحد
    0.93
     ensin
    0.86
     thiết
    0.85
     Cass
    0.83
    ต้อง
    0.83
    важа
    0.82
     Joined
    0.81
    gari
    0.81
    Activations Density 0.006%

    No Known Activations