© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36825
    Prev
    Next
    INDEX
    Explanations

    Cruel, dangerous, smile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    нки
    1.20
    нта
    1.16
    та
    1.09
    ת
    1.09
    יות
    1.01
    ت
    1.01
    нка
    0.97
    ং
    0.97
     treaties
    0.96
    мо
    0.96
    POSITIVE LOGITS
    Пер
    1.11
    ‌ನ
    1.08
     ArrayAdapter
    0.91
    ल्लिंग
    0.90
    Ра
    0.89
     empê
    0.88
    র্ষি
    0.88
    Ι
    0.88
    ۗ
    0.87
    Р
    0.87
    Activations Density 0.001%

    No Known Activations