© 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. 72189
    Prev
    Next
    INDEX
    Explanations

    XML tags, code snippets, Nitric, Q

    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
    וּ
    -1.80
     or
    -1.78
     this
    -1.76
    Mű
    -1.42
     бампер
    -1.39
     mengerti
    -1.39
     that
    -1.39
     bekym
    -1.37
    middag
    -1.34
     rengi
    -1.34
    POSITIVE LOGITS
    ׇ
    1.46
    ᾷ
    1.41
     dnes
    1.40
    ícias
    1.39
     الرئيسي
    1.35
     bezeichnet
    1.30
     cuadrados
    1.27
     ponownie
    1.27
     ’
    1.25
    事实上
    1.24
    Activations Density 0.006%

    No Known Activations