© 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. 73011
    Prev
    Next
    INDEX
    Explanations

    required fields

    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
    \\
    -1.77
    )
    -1.70
     {
    
    -1.55
     рассказать
    -1.54
    たつ
    -1.49
     Permalink
    -1.47
    いだ
    -1.46
     với
    -1.46
     \
    -1.43
    嗒
    -1.41
    POSITIVE LOGITS
    皤
    1.88
    that
    1.73
    辔
    1.57
    🛇
    1.52
    LOUIS
    1.51
    些什么
    1.49
     damska
    1.48
    كات
    1.48
    only
    1.48
     adanya
    1.47
    Activations Density 0.007%

    No Known Activations