© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48374
    Prev
    Next
    INDEX
    Explanations

    Xiamen, Fujian, China

    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_40_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
     Wars
    0.38
     sce
    0.38
     تحليل
    0.38
    =:
    0.37
    ဆို
    0.37
     丨
    0.37
     Conditioning
    0.37
    izma
    0.36
    apk
    0.36
    ᠶ
    0.36
    POSITIVE LOGITS
    闽
    0.74
    厦门
    0.64
    漳
    0.64
    閩
    0.64
    福建
    0.63
    厝
    0.61
    莆
    0.61
    蟳
    0.59
     Fuj
    0.58
    芗
    0.58
    Activations Density 0.016%

    No Known Activations