© 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. 12220
    Prev
    Next
    INDEX
    Explanations

    thanks followed by name

    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
     you
    -1.83
    woordig
    -1.77
     it
    -1.67
     utilice
    -1.61
    ſelves
    -1.61
    苌
    -1.60
    瑧
    -1.59
    佮
    -1.53
     χρησιμοποι
    -1.48
    嗄
    -1.48
    POSITIVE LOGITS
    or
    1.74
    ֎
    1.61
    ab
    1.55
    基本上
    1.53
    us
    1.51
    主要是
    1.48
     {
    1.48
    ur
    1.46
     clase
    1.45
    gmail
    1.45
    Activations Density 0.011%

    No Known Activations