© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47804
    Prev
    Next
    INDEX
    Explanations

    comparison phrases with that or those

    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
    ᷇
    -1.78
     Inſ
    -1.70
    kemeja
    -1.61
    敌人
    -1.59
    蛲
    -1.58
    ಂಗ
    -1.57
    鱨
    -1.57
    кета
    -1.57
     ۵
    -1.55
     ۴
    -1.55
    POSITIVE LOGITS
     which
    2.03
     in
    1.80
     we
    1.56
     while
    1.48
     to
    1.46
     when
    1.42
     of
    1.40
     others
    1.40
     always
    1.38
    したので
    1.38
    Activations Density 0.019%

    No Known Activations