Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8519
    Prev
    Next
    INDEX
    Explanations

    tables and lookups

    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
    TNode
    -0.82
    bilde
    -0.80
    jš
    -0.77
     Personen
    -0.75
    objc
    -0.71
    褴
    -0.70
     hát
    -0.70
     bataille
    -0.69
    jewel
    -0.69
    pila
    -0.68
    POSITIVE LOGITS
     tables
    4.03
     table
    4.03
     lookup
    3.16
     Tables
    2.95
    table
    2.95
    Table
    2.89
     Table
    2.88
    tables
    2.83
     табли
    2.81
    Tables
    2.77
    Activations Density 0.088%

    No Known Activations