© 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. 3550
    Prev
    Next
    INDEX
    Explanations

    code, security, and text snippets

    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
     dise
    -0.86
     pog
    -0.84
    DIRECT
    -0.80
     incontr
    -0.76
     lom
    -0.76
    到这里
    -0.76
    Tutorial
    -0.73
     Equi
    -0.72
     tė
    -0.72
     广告
    -0.71
    POSITIVE LOGITS
    USART
    0.83
    Ź
    0.80
    んび
    0.79
     EventType
    0.78
     cartridges
    0.77
    kanal
    0.77
     mourut
    0.77
     SearchView
    0.76
     riders
    0.75
     vueltas
    0.75
    Activations Density 0.013%

    No Known Activations