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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110379
    Prev
    Next
    INDEX
    Explanations

    The followed by formal documents

    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
     ajudá
    -1.13
     ám
    -1.07
     trató
    -1.02
     reduzir
    -1.01
     respetu
    -1.00
     např
    -0.99
     geralmente
    -0.98
     oídos
    -0.98
     valiente
    -0.96
    krish
    -0.95
    POSITIVE LOGITS
     contento
    1.28
    该
    1.27
     ragu
    1.13
     luci
    1.08
     crudo
    1.06
    Зміст
    1.05
     vini
    1.05
     barca
    1.04
     牛肉
    1.04
     maris
    1.02
    Activations Density 0.271%

    No Known Activations