© 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. 82948
    Prev
    Next
    INDEX
    Explanations

    pleading/leaned

    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
     økonom
    0.47
     문의
    0.47
     其中
    0.46
     鞋
    0.46
     ？
    0.46
     የስ
    0.45
     اقتص
    0.45
    ：《
    0.43
    咉
    0.43
    ："
    0.41
    POSITIVE LOGITS
    пле
    0.50
    тропо
    0.47
     leaning
    0.46
     прошу
    0.45
    ágenes
    0.44
    and
    0.43
    sores
    0.43
    o
    0.43
     pleading
    0.43
     leaned
    0.43
    Activations Density 0.001%

    No Known Activations