© 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. 103609
    Prev
    Next
    INDEX
    Explanations

    motive or reason

    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
    With
    -2.89
    I
    -2.56
    沒有
    -2.52
    /**
    -2.48
     impressively
    -2.42
    学校の
    -2.41
    (
    -2.39
    蠵
    -2.38
     keluarganya
    -2.34
    namentales
    -2.33
    POSITIVE LOGITS
    ☫
    3.56
    圌
    3.38
    
    2.78
    ჻
    2.72
    
    2.58
    ⮑
    2.41
    辚
    2.31
     acclaimed
    2.31
    が付いて
    2.30
    鉏
    2.27
    Activations Density 0.003%

    No Known Activations