© 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. 22-GEMMASCOPE-RES-131K
    7. 79519
    Prev
    Next
    INDEX
    Explanations

    car descriptions

    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_22/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
     their
    -1.34
     jejich
    -1.31
     kuhusu
    -1.30
     nuevos
    -1.27
     их
    -1.27
     they
    -1.25
     new
    -1.23
     miljoner
    -1.23
     ellos
    -1.23
     hned
    -1.22
    POSITIVE LOGITS
     huo
    1.66
     mahu
    1.63
     kuah
    1.55
     gari
    1.55
     kue
    1.53
     raha
    1.53
    şağı
    1.50
     keh
    1.48
     maal
    1.47
     kutu
    1.42
    Activations Density 0.021%

    No Known Activations