© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6635
    Prev
    Next
    INDEX
    Explanations

    Iranian, Persian, Iran

    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_31_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
    纽约
    0.57
    鲔
    0.55
     przej
    0.54
    西兰
    0.53
    屿
    0.53
    ły
    0.52
    amię
    0.52
    躏
    0.51
     নিউইয়
    0.50
    东京
    0.50
    POSITIVE LOGITS
     Iranian
    1.84
     Iran
    1.82
     Iranians
    1.63
     Tehran
    1.59
    Iran
    1.56
     iran
    1.56
    伊朗
    1.55
     Persian
    1.50
    Iranian
    1.49
     İran
    1.48
    Activations Density 0.023%

    No Known Activations