© 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. 80679
    Prev
    Next
    INDEX
    Explanations

    HTML tables

    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
    ازات
    -0.78
    ahuje
    -0.71
    bindValue
    -0.71
     WARRANTIES
    -0.71
    AnimationsModule
    -0.70
     nějak
    -0.69
     ві
    -0.69
     bonus
    -0.69
    脚注
    -0.68
     Versuch
    -0.68
    POSITIVE LOGITS
     Table
    1.91
     table
    1.85
    <table>
    1.84
    Table
    1.72
     tables
    1.57
    table
    1.55
     TABLE
    1.55
    TABLE
    1.38
     Tables
    1.37
    getTable
    1.34
    Activations Density 0.027%

    No Known Activations