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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2692
    Prev
    Next
    INDEX
    Explanations

    logical or disjunction

    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_34/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
    そして
    -1.59
     Hogar
    -1.32
    &&(
    -1.32
     GRATU
    -1.28
     Irlanda
    -1.25
     &&
    -1.25
     SimpleName
    -1.24
     vinaigre
    -1.23
    wój
    -1.22
    ołnier
    -1.22
    POSITIVE LOGITS
     or
    7.94
     или
    4.66
     hoặc
    4.00
     یا
    3.64
    或者
    3.61
    或是
    3.56
    或
    3.44
     หรือ
    3.33
    หรือ
    3.22
     oppure
    3.14
    Activations Density 0.022%

    No Known Activations