© 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. 182328
    Prev
    Next
    INDEX
    Explanations

    promoting public awareness

    np_acts-logits-general · gemini-2.5-flash-lite

    generating convincing misinformation

    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
     来
    0.52
    看来
    0.49
     开
    0.49
     ግራም
    0.49
    来看看
    0.49
     choir
    0.49
    构建
    0.49
    年纪
    0.47
     חו
    0.46
     จํานวน
    0.46
    POSITIVE LOGITS
    اش
    0.68
    مل
    0.61
    نوان
    0.57
    وات
    0.53
    اد
    0.50
    اع
    0.49
    ي
    0.48
    うえ
    0.47
    وص
    0.47
    SEVERE
    0.47
    Activations Density 0.000%

    No Known Activations