© 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. 45736
    Prev
    Next
    INDEX
    Explanations

    two, pair, both

    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
    jur
    -0.80
    uuml
    -0.73
    Perd
    -0.73
     böyle
    -0.73
     fö
    -0.72
    elfde
    -0.68
    нью
    -0.67
    り物
    -0.66
     接口
    -0.66
     Hodges
    -0.66
    POSITIVE LOGITS
    combined
    1.27
     combined
    1.25
    Pair
    1.23
     dwóch
    1.21
     zweimal
    1.17
    Combined
    1.13
     twice
    1.12
    BOTH
    1.11
    这两个
    1.03
     δύο
    1.03
    Activations Density 0.064%

    No Known Activations