© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    at the same time

    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>
    -2.19
    ↵↵↵
    -2.08
    ↵↵↵↵↵
    -1.96
     when
    -1.90
     that
    -1.80
    ↵↵↵↵↵↵
    -1.72
    ↵↵↵↵↵↵↵↵↵
    -1.70
    ↵↵↵↵↵↵↵
    -1.66
    ↵↵↵↵
    -1.63
    ↵↵↵↵↵↵↵↵
    -1.55
    POSITIVE LOGITS
     ſta
    1.68
    ейчас
    1.64
    怱
    1.63
     beaucoup
    1.63
     procès
    1.59
    eſ
    1.55
     Шаг
    1.55
    鸲
    1.54
    
    1.54
    氿
    1.52
    Activations Density 0.005%

    No Known Activations