© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79503
    Prev
    Next
    INDEX
    Explanations

    work

    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
    Negative Logits
    桄
    -1.19
    糶
    -1.19
    ༈
    -1.17
    ทำงาน
    -1.09
     camión
    -1.02
    ⩴
    -0.98
     pracuje
    -0.98
     working
    -0.98
     เท
    -0.98
     equipamiento
    -0.97
    POSITIVE LOGITS
     ethic
    1.90
     wonders
    1.28
    spaces
    1.24
    horse
    1.10
     miracles
    1.07
    arounds
    1.01
     horrified
    0.98
     ethics
    0.96
     done
    0.93
     strange
    0.93
    Activations Density 0.121%

    No Known Activations