© 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. 121610
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words

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

    explaining concepts and challenges

    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
     論
    0.53
     高級
    0.52
     উদ্ধ
    0.51
     రెండు
    0.51
     圖
    0.49
     プラ
    0.48
     三角
    0.48
     ビジネス
    0.47
     တစ်
    0.46
     还
    0.46
    POSITIVE LOGITS
     dracon
    0.49
    য়োজন
    0.44
    世界上
    0.44
    极端
    0.42
     Catholics
    0.42
    fono
    0.42
     معنی
    0.42
    ยาย
    0.41
    อยู่ใน
    0.41
     है
    0.40
    Activations Density 0.001%

    No Known Activations