© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63824
    Prev
    Next
    INDEX
    Explanations

    Coast Guard

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is detect mentions of the U.S. Coast Guard.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    谢谢
    -0.81
    "]
    -0.81
     盆
    -0.80
    地図
    -0.79
    esercito
    -0.78
     Condensed
    -0.77
     battleship
    -0.77
     Alamos
    -0.75
    Registers
    -0.75
     armies
    -0.75
    POSITIVE LOGITS
     Coast
    1.47
     cutter
    1.23
    Coast
    1.12
     cutters
    1.00
     CG
    0.96
    CG
    0.93
     Response
    0.90
     Cutter
    0.90
    cutter
    0.89
     response
    0.88
    Activations Density 0.016%

    No Known Activations