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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 28926
    Prev
    Next
    INDEX
    Explanations

    I followed by a verb

    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
     necessárias
    -1.70
     which
    -1.64
    鶺
    -1.60
     first
    -1.57
     while
    -1.50
    ınızı
    -1.45
     Diciembre
    -1.45
     investigação
    -1.42
    ↵↵↵
    -1.40
     Trá
    -1.39
    POSITIVE LOGITS
    Of
    1.66
    ar
    1.59
    搽
    1.56
    acker
    1.55
    ated
    1.54
    当然
    1.52
    各种
    1.51
    ،
    1.50
    部分
    1.49
    ৢ
    1.49
    Activations Density 0.029%

    No Known Activations