© 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. 101804
    Prev
    Next
    INDEX
    Explanations

    words in many 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_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
     {
    -1.99
     his
    -1.95
    {
    -1.91
    st
    -1.91
     THE
    -1.84
    ll
    -1.83
    }
    -1.78
     our
    -1.77
    -1.66
    re
    -1.66
    POSITIVE LOGITS
    ”，
    1.83
     skriva
    1.76
     profonde
    1.76
     näm
    1.74
    目前的
    1.73
    Sabato
    1.73
     brune
    1.71
     découver
    1.70
     травня
    1.67
     LEONARD
    1.66
    Activations Density 0.006%

    No Known Activations