© 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. 10-GEMMASCOPE-RES-131K
    4. 105739
    Prev
    Next
    INDEX
    Explanations

    new date or object instantiation

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

    The neuron fires on programming‐language reserved words and built‐in constants/functions (e.g. null/None, new, class, array, c, DateTime, 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
     of
    -1.93
    ◜
    -1.22
     with
    -1.21
    嗨
    -1.14
    メルカリ
    -1.13
    .
    
    -1.12
     esternos
    -1.11
    生活中
    -1.10
     『
    -1.10
     focused
    -1.09
    POSITIVE LOGITS
    oczes
    1.47
     anledning
    1.34
    erweise
    1.27
     Strukt
    1.23
    datei
    1.21
    ulose
    1.19
     akku
    1.17
     ⓒ
    1.16
     himo
    1.15
     måte
    1.15
    Activations Density 0.095%

    No Known Activations