© 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. 11627
    Prev
    Next
    INDEX
    Explanations

    interaction between

    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
    有關
    -2.28
    不錯
    -2.20
    琑
    -2.19
    𞤤
    -2.06
     如果
    -2.00
    でて
    -1.95
    锖
    -1.91
    釭
    -1.91
     Если
    -1.89
     начали
    -1.85
    POSITIVE LOGITS
    霂
    2.73
     of
    2.17
    rierten
    2.11
    呖
    1.91
    و
    1.91
    瘓
    1.90
    是由
    1.88
    brainer
    1.87
    墬
    1.87
    鸦
    1.86
    Activations Density 0.000%

    No Known Activations