© 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. 2034
    Prev
    Next
    INDEX
    Explanations

    match words or pairs

    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
    싱
    -0.73
    һы
    -0.73
    wea
    -0.71
    Google
    -0.71
    vanju
    -0.70
     menjelaskan
    -0.70
    眶
    -0.69
    于是
    -0.69
     skipping
    -0.68
    LJ
    -0.66
    POSITIVE LOGITS
     matching
    1.97
     matched
    1.77
    matching
    1.69
     Matching
    1.56
    Matching
    1.55
    matched
    1.49
     paired
    1.45
     pairs
    1.38
     flipped
    1.35
     match
    1.34
    Activations Density 0.012%

    No Known Activations