© 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. 34-GEMMASCOPE-RES-131K
    7. 57392
    Prev
    Next
    INDEX
    Explanations

    parts of compound terms

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

    The neuron strongly activates on romanized Chinese names written in pinyin with tonal diacritics.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    𝟗
    -0.76
    Ainda
    -0.76
    Apesar
    -0.74
    🚊
    -0.72
     girlfriends
    -0.71
    ศาสตร์
    -0.68
    nfs
    -0.68
    licken
    -0.68
     GMA
    -0.68
    Mesmo
    -0.68
    POSITIVE LOGITS
    Chal
    0.88
     Chal
    0.87
     chlor
    0.82
     Valentin
    0.72
     Gallagher
    0.72
    ักษ
    0.70
     Nest
    0.69
     chassis
    0.69
    puff
    0.67
     etre
    0.67
    Activations Density 0.027%

    No Known Activations