© 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. 64049
    Prev
    Next
    INDEX
    Explanations

    Erasmus Plus mobility

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

    The neuron fires on the labeled heading lines and metadata of an EU‐funded “KA2 Youth” Erasmus+ project (e.g. acronyms like KA2, Erasmus Plus, project titles, and their associated numbers).

    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
    campaigns
    -0.79
     savo
    -0.68
     zou
    -0.67
     inwest
    -0.66
    上学
    -0.66
    Four
    -0.66
    accumulative
    -0.65
     없는
    -0.65
     Campaigns
    -0.65
    little
    -0.65
    POSITIVE LOGITS
     mobility
    2.39
     Erasmus
    2.14
     Mobility
    1.87
    Mobility
    1.80
    Eras
    1.77
    mobility
    1.73
     exchange
    1.61
    exchange
    1.50
     mobilité
    1.44
    Exchange
    1.38
    Activations Density 0.014%

    No Known Activations