© 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. 56847
    Prev
    Next
    INDEX
    Explanations

    route snapshot

    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
    zones
    -0.81
    AppDelegate
    -0.77
     выступа
    -0.76
     zones
    -0.74
    onekana
    -0.72
    neighborhood
    -0.71
    itates
    -0.71
     rarement
    -0.71
     Syllabus
    -0.69
     手作り
    -0.69
    POSITIVE LOGITS
     route
    1.23
    route
    1.13
     ActivatedRoute
    1.09
     snapshot
    1.06
    snapshot
    0.95
     router
    0.94
    Snapshot
    0.94
     Route
    0.92
    路由
    0.92
    params
    0.90
    Activations Density 0.011%

    No Known Activations