© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79198
    Prev
    Next
    INDEX
    Explanations

    goods and retailers

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

    business goods and operations

    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
    團隊
    0.46
    潛行
    0.45
    穆
    0.44
    鞘
    0.43
    チーム
    0.42
    ができる
    0.42
     percobaan
    0.42
    偉
    0.42
    傑
    0.42
     fearless
    0.41
    POSITIVE LOGITS
     Aesthetics
    0.48
     خبری
    0.47
     retailers
    0.47
     merchants
    0.46
     aesthetics
    0.46
     entertainment
    0.46
     Goods
    0.46
    χος
    0.43
     товаров
    0.43
     товары
    0.43
    Activations Density 0.004%

    No Known Activations