© 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. 34-GEMMASCOPE-RES-131K
    7. 118516
    Prev
    Next
    INDEX
    Explanations

    "Field of the Invention" or "Geometric mean"

    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
     tenido
    -0.91
     zwier
    -0.88
     problemu
    -0.83
    ائمة
    -0.83
    をや
    -0.82
    都不能
    -0.82
    になれる
    -0.79
     spécialement
    -0.79
     odkry
    -0.79
    demy
    -0.77
    POSITIVE LOGITS
    ذت
    1.08
    罗
    0.96
    avadoc
    0.94
    ય
    0.88
    ارو
    0.88
    低
    0.87
    日
    0.86
    هور
    0.86
     raga
    0.85
    Similarly
    0.85
    Activations Density 0.003%

    No Known Activations