© 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. 19501
    Prev
    Next
    INDEX
    Explanations

    split or splitting strings and concepts

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

    The neuron fires on occurrences of the word “split” (including its forms like “splitting”) across compounds and phrases.

    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
    ↵↵
    -2.47
    .
    -2.44
    {
    -1.74
    >
    -1.74
     hilfre
    -1.54
     allow
    -1.48
     sparked
    -1.45
    datable
    -1.45
     TIEMPO
    -1.43
     Quais
    -1.41
    POSITIVE LOGITS
    split
    2.33
     splitting
    2.22
     split
    2.06
     Split
    1.95
    Split
    1.82
    i
    1.80
     splits
    1.80
     splitter
    1.78
    SPLIT
    1.71
    。  
    1.67
    Activations Density 0.022%

    No Known Activations