© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124050
    Prev
    Next
    INDEX
    Explanations

    concrete followed by specifics

    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
    {
    -3.41
    ING
    -3.34
    不是
    -2.88
    h
    -2.81
    没有
    -2.80
    ce
    -2.64
    真的是
    -2.58
     OF
    -2.53
    知道
    -2.52
    想
    -2.52
    POSITIVE LOGITS
    酲
    3.27
    龊
    3.09
    仄
    2.95
    鋮
    2.92
     撮っ
    2.84
    
    2.81
    驀
    2.80
    脔
    2.77
    谵
    2.73
    みたいです
    2.67
    Activations Density 0.002%

    No Known Activations