© 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. 38536
    Prev
    Next
    INDEX
    Explanations

    sequence of numbers and operators

    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
    ☫
    -1.91
    </h3>
    -1.64
    ף
    -1.60
     mereka
    -1.59
    oteur
    -1.56
    zości
    -1.52
     ils
    -1.52
    yelitis
    -1.49
    制的
    -1.49
    uatan
    -1.45
    POSITIVE LOGITS
    </b>
    2.70
     アンド
    1.84
     everything
    1.78
     Tämä
    1.58
     pescoço
    1.55
    .
    1.55
     chapéu
    1.54
    {
    1.52
     trovano
    1.48
     situazione
    1.48
    Activations Density 0.005%

    No Known Activations