© 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. 105854
    Prev
    Next
    INDEX
    Explanations

    wearable devices and technology

    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
    hahahaha
    -1.77
    屄
    -1.72
    ܔ
    -1.71
    """.
    -1.68
    纔
    -1.68
     sierp
    -1.66
    开来
    -1.66
     />);
    -1.65
    Tunisia
    -1.63
     maxWidth
    -1.62
    POSITIVE LOGITS
    <i>
    1.73
     tomando
    1.64
    小伙伴
    1.63
    AR
    1.57
    ↵↵
    1.56
     ciudadano
    1.55
    注意事
    1.51
     foremost
    1.50
    更大的
    1.45
    再次
    1.42
    Activations Density 0.033%

    No Known Activations