© 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. 1275
    Prev
    Next
    INDEX
    Explanations

    chest body

    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
    </strong>
    -1.89
    .
    -1.78
     danced
    -1.73
    塒
    -1.72
     vicente
    -1.68
    ја
    -1.67
     Mitarbeitern
    -1.66
    埽
    -1.66
    在我们
    -1.66
    ان
    -1.65
    POSITIVE LOGITS
     zusätz
    2.20
     \
    1.89
     ۶
    1.78
     mittler
    1.75
    艫
    1.74
     dön
    1.71
     ancha
    1.68
    噤
    1.67
    
    1.67
     acht
    1.65
    Activations Density 0.029%

    No Known Activations