© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117153
    Prev
    Next
    INDEX
    Explanations

    infrastructure development

    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
    দ্ধ
    -0.77
    %\[
    -0.74
     impotence
    -0.73
     любви
    -0.73
    ޯ
    -0.71
    #![
    -0.69
     @{
    -0.69
     rhestr
    -0.68
    :[{
    -0.68
    @$
    -0.68
    POSITIVE LOGITS
     infrastructure
    5.03
     Infrastructure
    3.48
    infrastructure
    3.39
    Infrastructure
    3.31
     infrastructures
    3.11
     infraestructura
    3.06
     инфраструк
    3.02
     infra
    3.00
     Infrastruktur
    2.64
     infrastruktur
    2.61
    Activations Density 0.032%

    No Known Activations