© 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. 48356
    Prev
    Next
    INDEX
    Explanations

    equestrian sports or horse-related events

    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
     UIImageView
    -0.83
     scala
    -0.80
     Loeb
    -0.80
    outputs
    -0.78
     Chadwick
    -0.77
    Ӏ
    -0.76
    protos
    -0.76
     technolog
    -0.76
     analogs
    -0.75
     jump
    -0.75
    POSITIVE LOGITS
     horses
    1.01
     AQ
    0.97
    fut
    0.94
    AQ
    0.85
     Texas
    0.85
     Wrangler
    0.84
     Pferd
    0.80
     Congress
    0.79
    Fut
    0.79
     NR
    0.77
    Activations Density 0.004%

    No Known Activations