© 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. 97957
    Prev
    Next
    INDEX
    Explanations

    Vue.js framework

    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
    ⁱ
    -0.88
    vägen
    -0.86
     Pittsburgh
    -0.85
    pygame
    -0.83
     pygame
    -0.83
    JspWriter
    -0.82
     desesper
    -0.81
    еди
    -0.80
    glUniform
    -0.80
    dj
    -0.79
    POSITIVE LOGITS
     culoare
    0.84
     Catcher
    0.81
    原型
    0.80
     Sandwiches
    0.80
     baisse
    0.80
    творення
    0.79
     popu
    0.77
     quartzite
    0.77
     Ramen
    0.77
     marbles
    0.77
    Activations Density 0.014%

    No Known Activations