© 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-65K
    7. 8938
    Prev
    Next
    INDEX
    Explanations

    code component definitions and tests

    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_65k_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
    类的
    0.54
    class
    0.50
     class
    0.48
    クラス
    0.46
    类
    0.45
     타입
    0.45
     класу
    0.45
    类型
    0.44
     类
    0.44
     객
    0.43
    POSITIVE LOGITS
     gacche
    0.44
     balconies
    0.41
     líquido
    0.41
     době
    0.41
     сигнала
    0.40
     Southerners
    0.40
     revoke
    0.39
     overturn
    0.39
    cano
    0.39
     času
    0.39
    Activations Density 0.014%

    No Known Activations