© 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. 3836
    Prev
    Next
    INDEX
    Explanations

    YY characters or sequences

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

    The neuron flags tokens made up of Latin letters with diacritical marks (e.g. Ý, ý, ě, ā, etc.).

    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
     schicken
    -2.42
    ↵
    -2.42
     bedeut
    -2.34
     メニュー
    -2.33
    H
    -2.31
    pecabe
    -2.25
    ஶ
    -2.23
    赜
    -2.20
    禤
    -2.20
    of
    -2.17
    POSITIVE LOGITS
    ’
    3.16
    s
    3.16
     ‘
    2.56
     は
    2.53
    芣
    2.48
    ی
    2.47
     versos
    2.36
    峮
    2.34
    呖
    2.31
    媖
    2.28
    Activations Density 0.002%

    No Known Activations