© 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. 70549
    Prev
    Next
    INDEX
    Explanations

    code, errors, diverse languages

    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
     we
    -2.83
     divulgação
    -2.72
    逦
    -2.56
     
    -2.42
    区别
    -2.42
    未能
    -2.38
    ゆく
    -2.36
    鸯
    -2.34
     streamlining
    -2.28
    風の
    -2.23
    POSITIVE LOGITS
     been
    2.77
    鸰
    2.72
    愎
    2.66
    など
    2.59
     всех
    2.58
     был
    2.55
    </h4>
    2.48
    ၠ
    2.48
    就好
    2.45
     выборе
    2.45
    Activations Density 0.001%

    No Known Activations