© 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. 70166
    Prev
    Next
    INDEX
    Explanations

    dry-bulk cargo, data indicates, synthetic regimes

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

    This neuron responds to technical terms and jargon related to maritime engineering and ship operations (e.g. engine-room roles, bulk carriers, hatches, navigation positions/distances).

    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
     customer
    -0.81
    vereignty
    -0.81
     operator
    -0.80
    blr
    -0.78
     dispatch
    -0.75
    منم
    -0.73
     subsidy
    -0.73
    شارة
    -0.73
    operator
    -0.72
     endnu
    -0.72
    POSITIVE LOGITS
     onboard
    0.85
     ово
    0.78
    舱
    0.77
    ụ
    0.75
     IMO
    0.75
    벌
    0.75
     cargo
    0.74
     Rockland
    0.73
    艙
    0.72
     Cargo
    0.72
    Activations Density 0.021%

    No Known Activations