© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 138657
    Prev
    Next
    INDEX
    Explanations

    pattern finding, specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    0.88
    lng
    0.78
    datos
    0.78
    ile
    0.75
    ls
    0.75
    0.73
    เรื่อง
    0.65
    اب
    0.65
    สำหรับ
    0.65
    ль
    0.64
    POSITIVE LOGITS
    ية
    0.89
    ي
    0.88
     Букмекеры
    0.86
     فونبټ
    0.82
     médio
    0.80
     κάν
    0.78
     መድሃኒ
    0.78
    ᱗
    0.78
    ᱸ
    0.77
    عين
    0.76
    Activations Density 0.000%

    No Known Activations