© 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. 13183
    Prev
    Next
    INDEX
    Explanations

    code ending punctuation

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

    The neuron activates on numeric literals (digit sequences) in code.

    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
     miliardi
    -1.06
     nuovi
    -0.98
    $-$
    -0.95
    atest
    -0.91
    濛
    -0.89
     cdti
    -0.89
     творчества
    -0.89
     MethodInfo
    -0.88
     kuan
    -0.88
    şte
    -0.88
    POSITIVE LOGITS
    <0xD6>
    0.98
    推荐阅读
    0.93
    ключение
    0.91
     vervol
    0.90
     by
    0.88
    他們
    0.85
    総評
    0.85
    按键
    0.84
    スペイン
    0.84
    おまけ
    0.84
    Activations Density 0.002%

    No Known Activations