© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102996
    Prev
    Next
    INDEX
    Explanations

    Voodoo, tribal, tribe

    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
    Not in Any Lists

    No Comments

    Negative Logits
     medieval
    -0.82
     kedi
    -0.82
     angels
    -0.81
     Trapp
    -0.81
     latin
    -0.80
     Ejecutivo
    -0.80
     Tudor
    -0.79
     maksi
    -0.78
    userdetails
    -0.78
    リエステル
    -0.78
    POSITIVE LOGITS
     tribe
    2.73
     tribal
    2.56
     tribes
    2.38
     Tribal
    2.08
    tribal
    2.06
    Tribal
    1.98
    tribe
    1.90
     Tribe
    1.85
    Tribe
    1.81
     chieftain
    1.73
    Activations Density 0.022%

    No Known Activations