© 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. 72165
    Prev
    Next
    INDEX
    Explanations

    JavaScript timing, interferometry, place names, Cineplex, Sindhu

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ized
    -2.78
    啭
    -2.72
    囿
    -2.63
    !’
    -2.59
    푣
    -2.44
    〜〜
    -2.41
     nji
    -2.39
    祘
    -2.39
    激情
    -2.39
    在我
    -2.36
    POSITIVE LOGITS
    {
    4.47
    ar
    3.22
     -
    2.97
     was
    2.64
     What
    2.45
     Also
    2.41
     --
    2.39
     For
    2.39
     Have
    2.38
     '
    2.31
    Activations Density 0.011%

    No Known Activations