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. 8033
    Prev
    Next
    INDEX
    Explanations

    daytime talk show hosts

    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
     isotropic
    -0.77
     Iv
    -0.74
     gas
    -0.73
     deepen
    -0.70
     remit
    -0.69
    瑟
    -0.69
    λω
    -0.68
    Iv
    -0.67
     Cretaceous
    -0.65
    Encyclopædia
    -0.65
    POSITIVE LOGITS
     daytime
    1.34
     Maury
    1.03
     Ellen
    1.01
     Oprah
    1.00
     Winfrey
    1.00
    Ellen
    0.96
    Show
    0.95
     Show
    0.90
     konflik
    0.89
     konflikt
    0.89
    Activations Density 0.023%

    No Known Activations