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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80667
    Prev
    Next
    INDEX
    Explanations

    code keywords and syntax

    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
     ながら
    -1.70
    萑
    -1.68
     He
    -1.64
     uniquement
    -1.63
    蒌
    -1.61
    Hvis
    -1.59
     chegar
    -1.58
     volledige
    -1.56
     comodidad
    -1.55
    buhan
    -1.54
    POSITIVE LOGITS
     jota
    1.75
     a
    1.59
    այի
    1.57
    britannien
    1.55
     dingin
    1.55
     WaitForSeconds
    1.54
     araba
    1.53
     akku
    1.52
     didik
    1.50
     sosis
    1.49
    Activations Density 0.001%

    No Known Activations