© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75695
    Prev
    Next
    INDEX
    Explanations

    marine vessels, Corps, environments

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

    The neuron is primarily detecting the token “Marine.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    “
    -2.92
     REALLY
    -2.91
     VERY
    -2.80
    ’
    -2.70
     Which
    -2.70
     Helpful
    -2.69
     craz
    -2.61
     ส์
    -2.47
     และ
    -2.39
     BECAUSE
    -2.38
    POSITIVE LOGITS
    </i>
    2.78
     notable
    2.75
     unparalleled
    2.69
    摭
    2.66
    
    2.63
    e
    2.58
    i
    2.52
    m
    2.50
    that
    2.47
    笮
    2.33
    Activations Density 0.012%

    No Known Activations