© 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. 105774
    Prev
    Next
    INDEX
    Explanations

    расчёт , определение , breakdown , considered

    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
    re
    -2.05
     finding
    -1.73
     localizar
    -1.69
     realised
    -1.67
     would
    -1.65
     başlad
    -1.64
    無い
    -1.63
     As
    -1.63
     должна
    -1.63
    をしました
    -1.62
    POSITIVE LOGITS
    3
    1.98
    0
    1.90
    \
    1.79
    ໊
    1.73
     jolly
    1.73
    ."
    1.72
    i
    1.70
    ᷆
    1.70
     мужчина
    1.70
     prachtige
    1.70
    Activations Density 0.005%

    No Known Activations