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. 8620
    Prev
    Next
    INDEX
    Explanations

    anniversary of events

    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
     stunning
    -1.01
     vorgesehen
    -0.99
    Външни
    -0.96
     combustível
    -0.96
    motic
    -0.94
    ないです
    -0.94
     sostiene
    -0.92
     delightful
    -0.92
     erwar
    -0.91
     suspensão
    -0.91
    POSITIVE LOGITS
     of
    2.64
     celebrations
    1.36
     celebration
    1.11
     year
    1.10
    🗓
    1.08
     edition
    1.08
     since
    1.07
    📆
    0.95
     Celebrations
    0.93
     bash
    0.93
    Activations Density 0.018%

    No Known Activations