© 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. 50053
    Prev
    Next
    INDEX
    Explanations

    Slavic first and last names

    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
     «
    -0.87
     wächst
    -0.86
    !!!
    -0.83
     is
    -0.81
    何况
    -0.79
     ''
    -0.79
    !!!!
    -0.78
    治愈
    -0.77
    雛
    -0.77
    協力
    -0.76
    POSITIVE LOGITS
     mahd
    1.21
     akku
    1.16
     REPLIES
    1.15
    vermectin
    1.09
    ureusement
    1.09
    Véase
    1.08
     bibit
    1.06
     tepung
    1.05
     sebelah
    1.04
     olev
    1.03
    Activations Density 0.030%

    No Known Activations