© 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. 11988
    Prev
    Next
    INDEX
    Explanations

    JPanel, LinearLayout, Islamabad, Niall Douglas

    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
    哢
    -2.81
    );
    -2.75
    i
    -2.67
    一種
    -2.59
     know
    -2.47
    ⮑
    -2.42
    杙
    -2.42
     organise
    -2.41
    Of
    -2.39
     také
    -2.39
    POSITIVE LOGITS
    with
    3.03
    ꜆
    2.91
    
    2.77
    
    2.77
    镦
    2.64
    鑁
    2.55
     カップル
    2.53
    昞
    2.50
    s
    2.48
    饪
    2.48
    Activations Density 0.003%

    No Known Activations