© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59292
    Prev
    Next
    INDEX
    Explanations

    dialog labels and quotes

    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
     ”
    -2.02
    到处
    -1.63
     icônes
    -1.56
    鹩
    -1.50
    攥
    -1.45
    地看着
    -1.44
    ’;
    -1.43
    ’:
    -1.43
    ↵↵↵↵↵↵↵↵↵↵
    -1.42
     巻
    -1.42
    POSITIVE LOGITS
     bustling
    1.67
     You
    1.66
    铂
    1.63
    使用方法
    1.59
     iglesia
    1.55
     bonitas
    1.50
    cartas
    1.48
    你想
    1.44
    łgorzata
    1.44
     confusion
    1.43
    Activations Density 0.002%

    No Known Activations