© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80751
    Prev
    Next
    INDEX
    Explanations

    last names with hyphens

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

    This neuron detects the hyphens that join parts of hyphenated 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
     recientemente
    -1.38
    除此之外
    -1.36
     time
    -1.30
     Ausblick
    -1.30
    ♪
    -1.25
     hinsichtlich
    -1.21
    vgg
    -1.18
     églises
    -1.17
     These
    -1.16
     Eindruck
    -1.16
    POSITIVE LOGITS
     who
    2.56
     whom
    1.82
    出来ました
    1.69
    nitř
    1.54
    できました
    1.53
    してました
    1.52
     problemas
    1.48
     saying
    1.47
    を行いました
    1.46
    を開催
    1.41
    Activations Density 0.029%

    No Known Activations