© 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. 34-GEMMASCOPE-RES-131K
    4. 33718
    Prev
    Next
    INDEX
    Explanations

    naval ship descriptions

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

    This neuron is triggered by naval ship names and designations (e.g., prefixes like HMS/USS, vessel names, hull numbers, and class identifiers).

    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
     airport
    -1.02
    Hombre
    -0.96
     fixa
    -0.94
    餡
    -0.91
     terbang
    -0.91
     Situationen
    -0.90
    đồng
    -0.89
     coger
    -0.89
    airline
    -0.89
    注意点
    -0.89
    POSITIVE LOGITS
     ship
    1.37
     ships
    1.30
     vessel
    1.27
     vessels
    1.23
     hull
    1.20
     naval
    1.18
     кора
    1.09
     tonnage
    1.09
     sunk
    1.09
    建造
    1.08
    Activations Density 0.098%

    No Known Activations