© 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. 42343
    Prev
    Next
    INDEX
    Explanations

    lodash functions and underscore usage

    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
    疍
    -2.30
    诒
    -2.30
    鉝
    -2.30
    輊
    -2.20
    utriche
    -2.19
     海洋
    -2.19
    
    -2.14
    硖
    -2.11
     häufigsten
    -2.08
    栳
    -2.06
    POSITIVE LOGITS
     
    2.14
     entice
    1.84
     «
    1.84
    <i>
    1.81
     So
    1.80
     -
    1.77
     一
    1.75
     Mischung
    1.75
     toute
    1.74
     как
    1.72
    Activations Density 0.005%

    No Known Activations