© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10686
    Prev
    Next
    INDEX
    Explanations

    surname prefixes and names

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

    The neuron strongly activates on capitalized family names (surnames) in multiword personal names.

    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
    If
    -2.00
     dirigez
    -1.70
     has
    -1.66
    the
    -1.65
    Since
    -1.61
    J
    -1.59
    When
    -1.55
    D
    -1.55
    するの
    -1.54
    齎
    -1.54
    POSITIVE LOGITS
    lijden
    1.45
    重的
    1.43
     appeler
    1.42
    mädchen
    1.41
    oncé
    1.41
    beding
    1.38
    setStroke
    1.38
     espoir
    1.37
    瞰
    1.35
    ኧ
    1.34
    Activations Density 0.039%

    No Known Activations