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. 7875
    Prev
    Next
    INDEX
    Explanations

    C# .NET types and collections

    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
     like
    -0.79
     양
    -0.75
     Reserve
    -0.75
    jamas
    -0.73
    Oro
    -0.71
     hur
    -0.71
    ImageData
    -0.70
     svil
    -0.69
     better
    -0.69
    ulo
    -0.68
    POSITIVE LOGITS
    Collection
    1.27
    EventHandler
    1.00
    collection
    0.90
    COLLECTION
    0.81
     collection
    0.79
     Collection
    0.78
    บค
    0.76
     recogida
    0.75
    httpMethod
    0.75
    ,',
    0.74
    Activations Density 0.065%

    No Known Activations