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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8084
    Prev
    Next
    INDEX
    Explanations

    contact information or specific terms

    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
     addItem
    -0.89
    leaflet
    -0.88
    öff
    -0.86
    antigua
    -0.84
     eene
    -0.82
    komend
    -0.82
    RIED
    -0.81
    וי
    -0.79
     十
    -0.78
     icônes
    -0.78
    POSITIVE LOGITS
     can
    0.90
    ุ่น
    0.82
     saludable
    0.80
    pagestyle
    0.79
     Abra
    0.79
    kanen
    0.78
     many
    0.78
     cannot
    0.77
    шне
    0.77
     литров
    0.76
    Activations Density 0.009%

    No Known Activations