© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57366
    Prev
    Next
    INDEX
    Explanations

    ships and vessels

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

    The neuron is tuned to detect specialized technical and industrial terminology—especially infrastructure and vessel designations (e.g. LNG terminal names, floating storage/regasification units, ship class and registry acronyms).

    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
     Demon
    -0.81
     Alien
    -0.71
     Folding
    -0.70
    Alien
    -0.70
     Touring
    -0.69
    يفة
    -0.69
     купа
    -0.69
    otus
    -0.68
     Stuff
    -0.66
    EDWARD
    -0.66
    POSITIVE LOGITS
     vessel
    1.80
     vessels
    1.50
    vessel
    1.44
     ship
    1.43
     Vessel
    1.30
    Vessel
    1.12
     ships
    1.09
    船
    1.08
    vessels
    0.98
    ship
    0.96
    Activations Density 0.032%

    No Known Activations