© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4206
    Prev
    Next
    INDEX
    Explanations

    country codes and other languages

    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_34/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
     it
    -0.96
    それは
    -0.95
     however
    -0.91
     каждому
    -0.90
    它们
    -0.89
    Each
    -0.82
     that
    -0.82
     each
    -0.81
     però
    -0.81
     how
    -0.80
    POSITIVE LOGITS
     then
    1.46
     there
    1.16
     там
    1.07
     até
    1.07
    Chef
    0.97
     before
    0.93
    XmlAccessType
    0.92
     tragé
    0.92
     allí
    0.92
     dann
    0.92
    Activations Density 0.007%

    No Known Activations