© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26993
    Prev
    Next
    INDEX
    Explanations

    repetition of elements or actions

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

    The neuron fires specifically on occurrences of the literal word “repeat.”

    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
    ↵↵
    -4.53
     {
    -3.52
    \
    -3.20
     <
    -2.72
     hacen
    -2.67
     terrific
    -2.45
     %
    -2.44
    {
    -2.42
     [
    -2.39
     avec
    -2.39
    POSITIVE LOGITS
    蟶
    3.19
     parachoque
    3.14
     火鍋
    3.14
    筚
    3.11
    獁
    2.95
    鷓
    2.89
    ڧ
    2.80
     parís
    2.80
    鐿
    2.78
    骝
    2.77
    Activations Density 0.011%

    No Known Activations