© 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. 29979
    Prev
    Next
    INDEX
    Explanations

    paths and journeys

    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
    ־ה
    -0.93
    ᶰ
    -0.92
     bateaux
    -0.90
     Vå
    -0.90
    ENSEN
    -0.90
    וּ
    -0.87
    呼ぶ
    -0.87
    nelle
    -0.87
    centered
    -0.86
    DllImport
    -0.86
    POSITIVE LOGITS
     path
    2.20
     journey
    1.98
     destination
    1.95
     paths
    1.88
     road
    1.65
     paved
    1.58
     destinations
    1.54
    destination
    1.49
    path
    1.48
     roads
    1.48
    Activations Density 0.057%

    No Known Activations