© 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. 81080
    Prev
    Next
    INDEX
    Explanations

    context or structure markers

    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
    放到
    -1.33
    放在
    -1.29
     in
    -1.29
     trong
    -1.22
    ใน
    -1.06
     today
    -1.04
    出现在
    -1.03
     στην
    -1.02
     here
    -1.02
     celý
    -1.00
    POSITIVE LOGITS
    的一些
    1.09
    的一
    1.09
    There
    1.05
     besonders
    1.03
    Those
    1.01
    ，
    0.97
     ebenfalls
    0.94
    rshire
    0.94
    ственная
    0.94
    These
    0.93
    Activations Density 0.005%

    No Known Activations