© 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. 20955
    Prev
    Next
    INDEX
    Explanations

    accented characters

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

    The main thing this neuron does is detect the lowercase letter "ó" (o with acute accent).

    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
    n
    -3.03
    s
    -3.00
    We
    -2.66
    ༑
    -2.55
    鉨
    -2.53
     люди
    -2.50
    劻
    -2.34
    Ꮵ
    -2.31
    C
    -2.28
     для
    -2.27
    POSITIVE LOGITS
     It
    2.84
    *
    2.45
     créée
    2.42
     tujuh
    2.38
     mangled
    2.28
    みてください
    2.22
     nommée
    2.22
    』、
    2.16
     delapan
    2.16
     utilisée
    2.06
    Activations Density 0.003%

    No Known Activations