© 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. 105146
    Prev
    Next
    INDEX
    Explanations

    "a la" or "alla" constructions

    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
     It
    -2.03
    .
    -1.91
     Since
    -1.88
     vollständ
    -1.84
     verstär
    -1.81
     yoke
    -1.80
    ла
    -1.74
    ↵↵
    -1.73
    hamilan
    -1.72
    ’,
    -1.69
    POSITIVE LOGITS
    茈
    2.13
    鼯
    1.98
    苤
    1.82
    iterations
    1.77
    囟
    1.72
    ”
    1.70
    acterísticas
    1.70
     them
    1.67
    出了
    1.66
    
    1.66
    Activations Density 0.002%

    No Known Activations