© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227211
    Prev
    Next
    INDEX
    Explanations

    mix into, refund a, petition ., cleaning habits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     améli
    0.54
    ล
    0.51
    ງ
    0.50
     gewährleisten
    0.49
    ító
    0.48
     வெற்ற
    0.48
     확률
    0.47
    书籍
    0.47
    柔软
    0.47
     низкой
    0.47
    POSITIVE LOGITS
     resided
    0.44
    傘
    0.42
    2
    0.41
     hMut
    0.40
    ”
    0.39
     Asalamualaikum
    0.39
     Sudan
    0.38
     contrasting
    0.38
    以上に
    0.38
    Table
    0.38
    Activations Density 0.001%

    No Known Activations