© 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. 56753
    Prev
    Next
    INDEX
    Explanations

    competition, conflict, coordination

    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
    uroy
    -0.88
     FERN
    -0.83
    雱
    -0.78
     veno
    -0.77
    ዶ
    -0.77
    镊
    -0.75
     kiin
    -0.74
     tamb
    -0.72
    ⸱
    -0.72
     COMBIN
    -0.72
    POSITIVE LOGITS
     competition
    8.19
    competition
    6.44
    Competition
    6.25
     Competition
    6.16
     competitive
    5.66
     compete
    5.44
     competing
    5.22
     competitors
    5.19
     competitions
    5.09
     competes
    4.97
    Activations Density 0.215%

    No Known Activations