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. 7831
    Prev
    Next
    INDEX
    Explanations

    code generation syntax

    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
    Nation
    -0.87
     nationally
    -0.84
     estação
    -0.80
    ásticos
    -0.75
     Př
    -0.75
     boun
    -0.75
     Yel
    -0.75
     Vý
    -0.73
     Macy
    -0.73
    amaran
    -0.71
    POSITIVE LOGITS
     araştır
    0.84
     همچنین
    0.83
     especialmente
    0.82
    Enciclopedia
    0.81
    πη
    0.81
    しますね
    0.81
     ansehen
    0.79
    這些
    0.79
     displayed
    0.77
    ⦊
    0.77
    Activations Density 0.003%

    No Known Activations