© 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. 98966
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming constructs

    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
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -2.64
     of
    -1.91
    ński
    -1.42
     kurios
    -1.38
    řízen
    -1.34
     simplemente
    -1.32
     teníamos
    -1.30
     sufri
    -1.29
     vaikka
    -1.27
     hjälpa
    -1.27
    POSITIVE LOGITS
     then
    2.14
     decisivo
    1.51
    + 
    1.51
    ワンピース
    1.48
    它们
    1.48
     horloge
    1.46
    憮
    1.45
     beliebtesten
    1.43
     vocale
    1.38
     andando
    1.37
    Activations Density 0.104%

    No Known Activations