© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86470
    Prev
    Next
    INDEX
    Explanations

    said to

    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
    哙
    -1.61
    篋
    -1.60
    嫪
    -1.50
    файл
    -1.50
     bekend
    -1.48
    trás
    -1.45
     què
    -1.45
    
    -1.45
     ét
    -1.43
    奩
    -1.43
    POSITIVE LOGITS
    0
    1.76
    ܜ
    1.65
    5
    1.60
     remarked
    1.57
    :
    1.48
    -
    1.48
    </i>
    1.45
     wykonane
    1.42
     SUCH
    1.39
    『
    1.33
    Activations Density 0.005%

    No Known Activations