© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 111
    Prev
    Next
    INDEX
    Explanations

    large, big, amounts, quantities

    np_acts-logits-general · gemini-2.5-flash-lite

    large amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     небольшой
    0.42
    写法
    0.42
     बिल्कुल
    0.40
     نہایت
    0.40
    様子
    0.39
    诨
    0.39
     짧
    0.38
    方式
    0.38
    极致
    0.38
     kleiner
    0.38
    POSITIVE LOGITS
     amounts
    0.83
     chunks
    0.82
     chunk
    0.80
     पैमाने
    0.77
     quantities
    0.75
     प्रमाणात
    0.75
    amounts
    0.74
     amount
    0.74
    chunk
    0.72
    काय
    0.72
    Activations Density 0.408%

    No Known Activations