© 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. 100554
    Prev
    Next
    INDEX
    Explanations

    connections between people

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

    healthier pregnancies, economic opportunities

    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
    错了
    0.50
    表达式
    0.46
    ི
    0.46
    改为
    0.46
    描述
    0.44
    咿
    0.44
    选择
    0.44
    塑料
    0.44
    璀
    0.43
    设置
    0.43
    POSITIVE LOGITS
     mantuvo
    0.53
     quotidien
    0.50
     protagonisti
    0.48
     മനു
    0.47
     cose
    0.46
     mantenere
    0.46
     डिलिव
    0.46
     mantener
    0.45
     pokud
    0.45
     manten
    0.45
    Activations Density 0.001%

    No Known Activations