© 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. 104815
    Prev
    Next
    INDEX
    Explanations

    that of / of the

    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
     and
    -1.85
    鱘
    -1.79
     fatis
    -1.77
     leyendo
    -1.76
    
    -1.75
     paff
    -1.73
    𖧷
    -1.73
    鯪
    -1.72
     escribiendo
    -1.72
    );
    -1.68
    POSITIVE LOGITS
     a
    2.38
    到底是
    1.96
    ⻬
    1.87
     forego
    1.81
     you
    1.78
    jarah
    1.77
    偏偏
    1.73
    我一直
    1.73
    した後
    1.73
     It
    1.72
    Activations Density 0.010%

    No Known Activations