© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43844
    Prev
    Next
    INDEX
    Explanations

    list item 2

    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
     if
    -1.98
     newly
    -1.77
     helps
    -1.57
     an
    -1.54
     epitom
    -1.52
     lavish
    -1.48
     because
    -1.42
    cadilly
    -1.40
     perpetually
    -1.36
      
    -1.33
    POSITIVE LOGITS
     goda
    1.71
    鮡
    1.70
     créer
    1.66
    闥
    1.65
     juſ
    1.64
    裢
    1.63
    .
    1.62
    borderSide
    1.62
    抟
    1.62
     afficher
    1.58
    Activations Density 0.022%

    No Known Activations