© 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. 115748
    Prev
    Next
    INDEX
    Explanations

    load capacity and support

    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
     first
    -0.77
    년
    -0.75
    Ạ
    -0.74
     nahm
    -0.72
    𝙰
    -0.70
    สม
    -0.69
     Respir
    -0.69
    ೧
    -0.69
    加入
    -0.69
     नहीं
    -0.69
    POSITIVE LOGITS
     capacity
    2.09
     load
    1.89
     capacities
    1.64
     تحمل
    1.61
     Capacity
    1.61
     maximum
    1.57
     capacidade
    1.55
     weight
    1.55
    capacity
    1.50
     capacidad
    1.48
    Activations Density 0.017%

    No Known Activations