© 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. 69556
    Prev
    Next
    INDEX
    Explanations

    programme

    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
    }
    -3.03
    鐿
    -2.61
    ]
    -2.53
    ꯷
    -2.47
    s
    -2.47
    휀
    -2.45
    嫱
    -2.44
    咴
    -2.41
    تیجه
    -2.34
    絎
    -2.31
    POSITIVE LOGITS
    焌
    2.95
    趵
    2.67
     were
    2.66
    
    2.59
    龊
    2.56
     juſ
    2.42
    呖
    2.39
     ſont
    2.31
    .
    2.31
     設計
    2.28
    Activations Density 0.005%

    No Known Activations