© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84287
    Prev
    Next
    INDEX
    Explanations

    calendar events and entries

    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
     poderia
    -0.99
     ซึ่ง
    -0.96
     recém
    -0.96
     necessário
    -0.95
     conhece
    -0.93
    ondern
    -0.92
    わざわざ
    -0.90
     lembra
    -0.88
    zeppelin
    -0.88
     crescendo
    -0.88
    POSITIVE LOGITS
    rrrrr
    1.19
    calendar
    1.00
     synchronization
    1.00
     appointments
    0.98
    📅
    0.96
    rrrrrr
    0.96
    🗓
    0.92
     Monats
    0.90
    Event
    0.89
    rrrrrrrr
    0.87
    Activations Density 0.012%

    No Known Activations