© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15024
    Prev
    Next
    INDEX
    Explanations

    motif or motifs

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

    The neuron detects occurrences of the word “motif.”

    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
    {
    -2.48
    歃
    -2.47
    鰱
    -2.36
    当即
    -2.34
    ी
    -2.28
    溦
    -2.23
    紧接着
    -2.22
    ઁ
    -2.20
     westfalen
    -2.14
    
    -2.14
    POSITIVE LOGITS
    '
    3.50
     adicionar
    2.45
     mostrar
    2.36
    鋐
    2.33
     如果
    2.31
     If
    2.30
    replyreport
    2.25
    荅
    2.22
     当
    2.17
     That
    2.13
    Activations Density 0.006%

    No Known Activations