© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114160
    Prev
    Next
    INDEX
    Explanations

    part of

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

    The neuron strongly activates on the word “part,” especially when it appears in phrases like “part of.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    あります
    -1.92
    They
    -1.81
    .
    -1.79
    That
    -1.78
    ㋛
    -1.76
    あるので
    -1.75
    炱
    -1.66
    輅
    -1.65
     “
    -1.63
    чера
    -1.61
    POSITIVE LOGITS
     of
    2.78
    ."
    2.30
    ，「
    1.80
    .''
    1.76
     ("
    1.69
     \'
    1.63
    ){
    1.63
    ("
    1.63
     затем
    1.60
    $>$
    1.59
    Activations Density 0.010%

    No Known Activations