© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8
    Prev
    Next
    INDEX
    Explanations

    signals intelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᅱ
    0.82
    ﻋ
    0.81
     девя
    0.80
    ﻟ
    0.78
     ছিলেন
    0.78
    D
    0.78
    ты
    0.77
    />
    0.76
    лением
    0.76
     furlough
    0.75
    POSITIVE LOGITS
    neſs
    0.78
    جراء
    0.75
    setRoi
    0.74
    ແລະ
    0.73
    硬盘
    0.73
     будь
    0.73
     داخلی
    0.72
    
    0.72
    数据库
    0.71
     питань
    0.71
    Activations Density 0.000%

    No Known Activations