© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117189
    Prev
    Next
    INDEX
    Explanations

    included words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̙
    -1.10
    購入
    -0.90
     toko
    -0.90
     场景
    -0.87
    使用方法
    -0.87
    ണ്ട
    -0.82
     venter
    -0.82
     結果
    -0.82
    Dock
    -0.81
     ليب
    -0.80
    POSITIVE LOGITS
     includes
    1.71
     included
    1.70
     inclusions
    1.60
     Includes
    1.59
    clusions
    1.58
     price
    1.54
     include
    1.52
     inclusive
    1.51
     Included
    1.48
    包含
    1.43
    Activations Density 0.017%

    No Known Activations