© 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. 29152
    Prev
    Next
    INDEX
    Explanations

    expressions of praise and admiration

    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
    攫
    -2.02
    異なります
    -1.68
    最重要
    -1.65
     in
    -1.63
     a
    -1.59
    巽
    -1.52
    暁
    -1.51
    穢
    -1.51
    🕗
    -1.49
    阅读原文
    -1.48
    POSITIVE LOGITS
    5
    2.16
     bicchiere
    1.59
     CONCLUSION
    1.59
    踯
    1.58
    8
    1.57
    腚
    1.55
    9
    1.54
     siguientes
    1.53
    缥
    1.52
     parecen
    1.48
    Activations Density 0.026%

    No Known Activations