© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10666
    Prev
    Next
    INDEX
    Explanations

    historical eras and empires

    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
    されている
    0.50
    >().
    0.47
    ጧ
    0.43
    <unused339>
    0.43
    <unused2013>
    0.43
     অন্যান্য
    0.41
    这类
    0.41
    曲线
    0.40
    <unused2017>
    0.40
    вате
    0.40
    POSITIVE LOGITS
     era
    0.75
    時代の
    0.62
     successor
    0.59
    successor
    0.59
    Era
    0.58
    時代
    0.57
     dönem
    0.55
     시절
    0.55
     эпоху
    0.54
     Era
    0.53
    Activations Density 0.077%

    No Known Activations