© 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. 59084
    Prev
    Next
    INDEX
    Explanations

    surname endings

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

    The neuron specialized in detecting subword fragments of personal names (e.g. bits of surnames) in citation‐style author listings.

    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
     of
    -2.00
    ícias
    -1.97
    鮸
    -1.71
     cleanse
    -1.70
    檍
    -1.66
     Then
    -1.65
     FACTS
    -1.64
    ients
    -1.61
     时尚
    -1.59
     camiset
    -1.58
    POSITIVE LOGITS
    ":[{
    1.77
     falleció
    1.73
     there
    1.66
     religiosas
    1.49
    lccn
    1.48
     sufrió
    1.46
     judíos
    1.45
     ocurrió
    1.44
     ebenfalls
    1.44
     entró
    1.41
    Activations Density 0.100%

    No Known Activations