© 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. 61276
    Prev
    Next
    INDEX
    Explanations

    Turkmenistan football, House Of Cards

    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
    〬
    -1.92
    ſelf
    -1.88
    神情
    -1.78
    後の
    -1.77
    🪤
    -1.77
     serían
    -1.75
     sería
    -1.72
    鹇
    -1.72
     sorgfäl
    -1.72
    眎
    -1.71
    POSITIVE LOGITS
    ↵↵
    2.00
    on
    1.86
    erencia
    1.70
    ذت
    1.61
     do
    1.60
    лика
    1.59
     profund
    1.58
    曁
    1.57
    óticos
    1.56
     amarillo
    1.55
    Activations Density 0.003%

    No Known Activations