© 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. 85191
    Prev
    Next
    INDEX
    Explanations

    lengthy report or explanation

    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
     still
    -1.43
     cerdas
    -1.35
     campeão
    -1.31
    {
    -1.30
     fez
    -1.25
     jederzeit
    -1.25
    andidates
    -1.24
     commencent
    -1.23
     Meilleures
    -1.23
     mín
    -1.23
    POSITIVE LOGITS
     how
    1.81
     why
    1.76
     but
    1.52
    length
    1.37
     بنابراین
    1.36
    他们
    1.34
    var
    1.30
    ("")){
    1.27
    人員
    1.22
     sensaciones
    1.21
    Activations Density 0.048%

    No Known Activations