© 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. 44440
    Prev
    Next
    INDEX
    Explanations

    proper nouns and abbreviations

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

    The neuron activates on capitalized named entities (proper nouns), such as people’s names, place names, organizations, and other titles.

    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
     demostr
    -1.96
     produc
    -1.77
     demás
    -1.71
     reaf
    -1.68
     engag
    -1.66
     ''
    -1.66
    歺
    -1.63
     touristes
    -1.61
     alrededores
    -1.59
     obvio
    -1.59
    POSITIVE LOGITS
     it
    1.98
    _
    1.74
     has
    1.74
     vinculado
    1.73
     having
    1.70
     mostrarse
    1.70
     provocado
    1.69
     могла
    1.67
     provocar
    1.63
     revelar
    1.63
    Activations Density 0.205%

    No Known Activations