© 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. 115989
    Prev
    Next
    INDEX
    Explanations

    dropdown menu or list

    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
     Luckily
    -0.95
    g
    -0.93
    下雨
    -0.92
    不忘
    -0.90
    y
    -0.87
     fantastic
    -0.85
    wanne
    -0.85
     lepid
    -0.83
    Leírás
    -0.82
    
    -0.82
    POSITIVE LOGITS
     menu
    1.29
    menu
    1.00
    メニュー
    0.97
     Januari
    0.91
     Item
    0.91
    mkdirs
    0.91
     menus
    0.90
    хіво
    0.89
     ४
    0.87
    祝い
    0.86
    Activations Density 0.005%

    No Known Activations