© 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. 111267
    Prev
    Next
    INDEX
    Explanations

    categorization and descriptive phrases

    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
    <td>
    -1.95
     our
    -1.83
     Hvis
    -1.64
    1
    -1.62
    磻
    -1.61
    معلومات
    -1.60
    ISHMENT
    -1.59
     eivät
    -1.59
     include
    -1.59
    鞋子
    -1.55
    POSITIVE LOGITS
     alemanes
    2.05
     эту
    1.91
     новая
    1.89
     funcionales
    1.81
     поддержка
    1.81
     queridos
    1.80
    遑
    1.75
     этих
    1.72
     bocetos
    1.72
     dormitorios
    1.71
    Activations Density 0.043%

    No Known Activations