© 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. 10-GEMMASCOPE-RES-131K
    7. 59196
    Prev
    Next
    INDEX
    Explanations

    American institutions and associations

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

    The neuron strongly activates on the word “American” when it appears in the names of professional or scientific organizations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     localización
    -1.86
    憷
    -1.77
    красный
    -1.76
     arcilla
    -1.74
     utilisés
    -1.72
     verhind
    -1.65
    ༑
    -1.65
     trám
    -1.64
     bambú
    -1.61
     surtido
    -1.59
    POSITIVE LOGITS
     of
    2.11
     any
    2.08
     all
    1.98
     not
    1.97
     even
    1.95
     What
    1.95
     what
    1.87
     that
    1.76
     figlia
    1.71
     Even
    1.67
    Activations Density 0.127%

    No Known Activations