© 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. 10-GEMMASCOPE-RES-131K
    7. 71694
    Prev
    Next
    INDEX
    Explanations

    Taoist, kendo, Dao

    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
     что
    -1.98
     этих
    -1.97
     ambayo
    -1.88
    ՚
    -1.83
    呓
    -1.80
    𐄙
    -1.79
     ‘‘
    -1.78
    そも
    -1.77
     abbia
    -1.76
    メニューは
    -1.75
    POSITIVE LOGITS
    ⇴
    2.02
     Aprend
    1.98
     curtail
    1.93
     elicit
    1.91
     Erfüllung
    1.89
    
    1.88
     الجديدة
    1.88
     Tienen
    1.87
     Begleitung
    1.87
    ֟
    1.84
    Activations Density 0.008%

    No Known Activations