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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8657
    Prev
    Next
    INDEX
    Explanations

    restaurants and premium services

    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
     BBQ
    -1.08
     cheap
    -0.99
     snacks
    -0.91
     barbecue
    -0.88
     rootView
    -0.86
     snack
    -0.85
     cafés
    -0.85
     arcade
    -0.83
    砾
    -0.82
    чы
    -0.81
    POSITIVE LOGITS
     Prime
    1.04
     martini
    1.00
     wine
    0.92
     Martini
    0.87
     cork
    0.84
     valet
    0.82
    wine
    0.81
     Prix
    0.80
     consistent
    0.80
     File
    0.79
    Activations Density 0.022%

    No Known Activations