© 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. 63460
    Prev
    Next
    INDEX
    Explanations

    maintaining and upkeep

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

    The neuron fires on words that describe financial expenses or upkeep (e.g. costs of operating and maintaining).

    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
    𝐔
    -0.81
    šanās
    -0.80
    նակ
    -0.79
     libération
    -0.78
     interceptions
    -0.78
    ivotopis
    -0.77
    orsk
    -0.76
     kraju
    -0.75
    micas
    -0.75
     trám
    -0.75
    POSITIVE LOGITS
     maintenance
    6.25
    maintenance
    4.91
    Maintenance
    4.72
     upkeep
    4.69
     Maintenance
    4.66
     maintain
    4.34
    维护
    3.98
     MAINTENANCE
    3.95
     maintaining
    3.88
     maintained
    3.83
    Activations Density 0.099%

    No Known Activations