© 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. 22-GEMMASCOPE-RES-131K
    7. 67403
    Prev
    Next
    INDEX
    Explanations

    ship designations and names

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

    The neuron activates on formal ship designations (e.g. "USS Hamlin (AV-15)", "HMS Flycatcher", hull numbers like AV-15, DD-552, etc.), i.e. proper naval vessel names and their classification codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     nuevos
    -1.05
     nueva
    -1.04
     discí
    -1.01
     nuovo
    -1.00
     آلمان
    -0.99
     nuevo
    -0.97
     věci
    -0.94
     tých
    -0.94
     chauffeur
    -0.94
     用意
    -0.94
    POSITIVE LOGITS
     when
    1.09
     توق
    1.05
     tdci
    1.02
     pleaf
    1.02
     bü
    1.00
     several
    1.00
    auce
    1.00
    💈
    0.99
     owned
    0.98
    
    0.98
    Activations Density 0.086%

    No Known Activations