© 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. 10-GEMMASCOPE-RES-131K
    7. 119618
    Prev
    Next
    INDEX
    Explanations

    build scripts and configurations

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "build" in technical configuration files and code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    $,
    -1.90
     wich
    -1.85
     должны
    -1.66
    鷽
    -1.66
    汩
    -1.66
    medriver
    -1.63
    vieron
    -1.62
    êts
    -1.60
    九年
    -1.57
     clínicas
    -1.54
    POSITIVE LOGITS
    (
    1.77
    ,
    1.68
     Gegensatz
    1.53
    >
    1.46
    歃
    1.45
     Process
    1.45
     biß
    1.44
    pisah
    1.42
    也
    1.41
     auseinander
    1.40
    Activations Density 0.050%

    No Known Activations