© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39700
    Prev
    Next
    INDEX
    Explanations

    foreign accents and pronunciation

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

    This neuron fires on occurrences of the string “accent” (in any form or context).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     But
    -2.67
    ”.
    -2.41
    皷
    -2.38
    ⸫
    -2.33
    та
    -2.28
     ポーズ
    -2.28
    ی
    -2.25
    とおり
    -2.22
     относятся
    -2.17
    ve
    -2.16
    POSITIVE LOGITS
    ↵
    2.86
    𖥦
    2.72
     sebagainya
    2.33
    Sekarang
    2.31
     и
    2.23
    Bukan
    2.17
    Tetapi
    2.17
    which
    2.17
    the
    2.16
    and
    2.13
    Activations Density 0.004%

    No Known Activations