© 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. 2485
    Prev
    Next
    INDEX
    Explanations

    barbarian savage backward 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
     estabilidad
    -0.74
     판
    -0.71
     manguera
    -0.71
     extraordinaria
    -0.68
     whales
    -0.66
    Biografi
    -0.66
     keuken
    -0.65
    atron
    -0.64
    uangan
    -0.63
    安く
    -0.63
    POSITIVE LOGITS
     barbarian
    2.98
     savage
    2.89
     barbarians
    2.88
     barbar
    2.83
     barbaric
    2.70
    barb
    2.63
     Barb
    2.44
     Barbarian
    2.44
    Barb
    2.42
     savages
    2.42
    Activations Density 0.035%

    No Known Activations