© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13870
    Prev
    Next
    INDEX
    Explanations

    days, numbers, and Picchu are important

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

    forms of 'is'

    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_31_width_16k_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
     ppl
    0.47
     পাইনি
    0.42
     بتوان
    0.41
    ﺶ
    0.41
     д
    0.40
     g
    0.39
     取っ
    0.39
    ド
    0.39
     increasing
    0.39
     사용하여
    0.38
    POSITIVE LOGITS
     merupakan
    1.16
     является
    1.09
     είναι
    1.05
     adalah
    1.03
     is
    0.98
    是一个
    0.95
     represents
    0.94
    是一個
    0.94
    是个
    0.91
     bukanlah
    0.89
    Activations Density 0.339%

    No Known Activations