© 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. 124165
    Prev
    Next
    INDEX
    Explanations

    Sanskrit and Asian names

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

    The neuron detects long‐vowel markers (letters with macrons or comparable diacritics) in transliterated text.

    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
    t
    -2.81
     }
    -2.52
     好看
    -2.50
     intrinsically
    -2.45
     siendo
    -2.34
     Öff
    -2.31
    :
    -2.31
     欣赏
    -2.20
    苹
    -2.19
    ↵
    -2.17
    POSITIVE LOGITS
    蹰
    2.92
    ’，
    2.86
     alamu
    2.86
     lanka
    2.83
    葙
    2.81
    螄
    2.75
     russes
    2.72
    驁
    2.72
     italiens
    2.56
    ⢓
    2.56
    Activations Density 0.000%

    No Known Activations