© 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. 101945
    Prev
    Next
    INDEX
    Explanations

    specific technical terms after "of"

    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
     purposes
    -1.81
    2
    -1.77
    (
    -1.62
     höchste
    -1.57
     /
    -1.55
    r
    -1.49
    al
    -1.47
    C
    -1.47
     gelieb
    -1.45
     Erwachsene
    -1.44
    POSITIVE LOGITS
     for
    3.02
    Ār
    1.64
     unſ
    1.58
    Ꮫ
    1.55
    炻
    1.51
     英語
    1.51
     iſt
    1.50
    
    1.48
     sprüche
    1.47
    ㅁ
    1.45
    Activations Density 0.297%

    No Known Activations