© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3027
    Prev
    Next
    INDEX
    Explanations

    The neuron fires most strongly on mentions of ships or naval deployments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    埼玉
    0.75
    栃
    0.71
     sidewalks
    0.70
     sidewalk
    0.68
     кирпи
    0.67
     коля
    0.67
    埼玉県
    0.67
     Bloomington
    0.67
    車
    0.66
     গান্ধ
    0.65
    POSITIVE LOGITS
     nautical
    2.70
     maritime
    2.69
    海上
    2.61
     seaf
    2.61
    船舶
    2.55
     marine
    2.52
    🛳
    2.50
     sailors
    2.48
    🚢
    2.47
    ⛵
    2.47
    Activations Density 1.422%

    No Known Activations