© 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. 21886
    Prev
    Next
    INDEX
    Explanations

    awk command usage

    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
    ’
    -2.56
    ,’
    -2.56
    ↵
    -2.42
    感じで
    -2.05
     ‘’
    -1.93
    ،
    -1.91
     هناك
    -1.88
     ‘‘
    -1.87
    ]
    -1.82
    
    -1.82
    POSITIVE LOGITS
     that
    2.02
    蕷
    1.95
     情侣
    1.95
    涠
    1.88
    釙
    1.84
    樒
    1.84
    屺
    1.82
    tuigen
    1.76
    ències
    1.74
     forKey
    1.73
    Activations Density 0.004%

    No Known Activations