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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6859
    Prev
    Next
    INDEX
    Explanations

    contrary to expectations

    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_24_width_16k_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
     متنوع
    0.80
     lainnya
    0.77
     weitere
    0.73
     다양한
    0.73
     dotyczą
    0.72
     различных
    0.72
     বিভিন্ন
    0.69
     beragam
    0.69
     weiteren
    0.69
    各类
    0.68
    POSITIVE LOGITS
     ironically
    0.96
    Ironically
    0.87
    居然
    0.84
     Ironically
    0.84
     irony
    0.81
     contrary
    0.80
     ironic
    0.80
    Contrary
    0.79
    Surprisingly
    0.79
     Contrary
    0.78
    Activations Density 0.726%

    No Known Activations