© 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. 10-GEMMASCOPE-RES-131K
    7. 48425
    Prev
    Next
    INDEX
    Explanations

    yacht and yacht clubs

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

    The neuron fires strongly on mentions of “yacht” and especially the phrase “Yacht Club,” i.e. references to yacht clubs.

    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
    瑨
    -3.13
    杮
    -2.75
     ส์
    -2.69
    缡
    -2.67
    縢
    -2.61
    䊏
    -2.61
    袮
    -2.61
    铪
    -2.53
    臯
    -2.47
    »,
    -2.42
    POSITIVE LOGITS
    :
    2.84
    L
    2.80
    A
    2.69
    2.66
    </i>
    2.66
    O
    2.48
    .
    2.39
     v
    2.33
    c
    2.30
    たちの
    2.23
    Activations Density 0.002%
    No Known Activations