© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103583
    Prev
    Next
    INDEX
    Explanations

    names and places

    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_10/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
     經典
    -2.58
    
    -2.55
    حتى
    -2.44
    ’，
    -2.39
    лтемелер
    -2.34
    嵓
    -2.28
    喈
    -2.17
    谖
    -2.16
    る
    -2.14
     ikke
    -2.13
    POSITIVE LOGITS
    薷
    2.38
     been
    2.31
     ausser
    2.23
    猛然
    2.09
    ՚
    2.05
     theses
    2.02
    讪
    2.02
     º
    2.00
    Награды
    1.98
     
    1.98
    Activations Density 0.002%

    No Known Activations