© 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. 34-GEMMASCOPE-RES-131K
    7. 116108
    Prev
    Next
    INDEX
    Explanations

    either/or choices

    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
    forall
    -1.38
     أي
    -1.16
     bất
    -1.12
    了很多
    -1.11
    任何
    -1.10
    струкция
    -1.09
     any
    -1.06
     might
    -1.02
     kanske
    -1.02
     oamen
    -1.02
    POSITIVE LOGITS
     either
    4.84
    either
    4.44
    Either
    3.94
     entweder
    3.66
     либо
    3.53
     Either
    3.44
     algún
    3.08
     varying
    2.97
     alguna
    2.95
    要么
    2.78
    Activations Density 0.406%

    No Known Activations