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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108854
    Prev
    Next
    INDEX
    Explanations

    special occasions and celebrations

    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
    quartz
    -0.88
    🐹
    -0.83
     muscles
    -0.77
    стых
    -0.75
    BOLD
    -0.75
    lld
    -0.74
     resultaat
    -0.73
    RequestOptions
    -0.73
    オブ
    -0.73
    /**
    -0.73
    POSITIVE LOGITS
     occasion
    2.81
     event
    2.42
     occasions
    2.25
    occasion
    2.02
     events
    1.97
     celebration
    1.94
     occas
    1.91
     milestone
    1.88
     important
    1.88
    event
    1.83
    Activations Density 0.044%

    No Known Activations