© 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. 7060
    Prev
    Next
    INDEX
    Explanations

    geological exploration and construction projects

    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
    isyon
    -0.83
    Shining
    -0.79
     ACTIVITIES
    -0.79
    mejores
    -0.78
     lỗ
    -0.77
    Xuất
    -0.75
    Desarrollo
    -0.74
    콰
    -0.72
    dirig
    -0.72
     Shining
    -0.72
    POSITIVE LOGITS
     project
    1.50
     projects
    1.10
     construction
    1.06
    project
    1.05
     Project
    1.01
     engineering
    1.01
     design
    0.99
     проект
    0.96
     investment
    0.95
    getProject
    0.93
    Activations Density 0.011%

    No Known Activations