© 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. 11001
    Prev
    Next
    INDEX
    Explanations

    real estate and names

    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
    尨
    -2.75
    鋮
    -2.11
    的多
    -2.09
    ✢
    -2.09
     However
    -2.08
    
    -2.08
     FYI
    -2.02
     aggravating
    -1.98
    2
    -1.98
    があり
    -1.97
    POSITIVE LOGITS
     інші
    2.72
    )
    2.70
    美国的
    2.59
    ⟝
    2.59
    {
    2.59
    菴
    2.58
    这个
    2.55
    这里
    2.39
    家乡
    2.38
    橚
    2.36
    Activations Density 0.001%

    No Known Activations