© 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. 72769
    Prev
    Next
    INDEX
    Explanations

    districts

    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
    ↵
    -2.88
     and
    -2.05
    </b>
    -1.99
    這些
    -1.94
     レスト
    -1.74
    他們
    -1.71
     these
    -1.70
     aray
    -1.70
    /
    -1.69
    人們
    -1.68
    POSITIVE LOGITS
    鹋
    1.88
    σταση
    1.87
     souligné
    1.86
    chiha
    1.84
    ⚥
    1.80
    玫
    1.77
     muitos
    1.73
    емое
    1.66
    小花
    1.63
    燹
    1.63
    Activations Density 0.007%

    No Known Activations