© 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. 126
    Prev
    Next
    INDEX
    Explanations

    interrogative words and 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
    
    -2.69
    。「
    -2.52
    <td>
    -2.42
    趼
    -2.41
    ",
    -2.39
     todėl
    -2.34
    廕
    -2.33
    </b>
    -2.30
    谖
    -2.30
    i
    -2.28
    POSITIVE LOGITS
    </em>
    2.86
    </strong>
    2.50
    ～　
    2.41
    みると
    2.41
    有不少
    2.38
    齶
    2.36
    </h3>
    2.34
    見ると
    2.27
    見ても
    2.27
    什么的
    2.19
    Activations Density 0.002%

    No Known Activations