© 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. 21767
    Prev
    Next
    INDEX
    Explanations

    in following descriptions

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

    words like "ago", "before", "shoulders"

    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
    リー
    0.44
     predom
    0.43
     worrisome
    0.43
    ೯
    0.43
    pyridazin
    0.42
    otroph
    0.41
     تباہ
    0.40
    вчи
    0.39
    촉
    0.38
    リエ
    0.37
    POSITIVE LOGITS
     这个
    0.46
     此
    0.46
     服务
    0.46
    的服务
    0.44
    检查
    0.44
     可以
    0.44
     数据
    0.43
     nello
    0.43
     一个
    0.43
     गुजराती
    0.43
    Activations Density 0.000%

    No Known Activations