© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7193
    Prev
    Next
    INDEX
    Explanations

    historical or cultural phrases

    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
    樱花
    -0.95
    ństw
    -0.91
     Playoffs
    -0.89
     aboriginal
    -0.88
     vinos
    -0.87
    センサー
    -0.85
     archeological
    -0.84
     civilized
    -0.83
     Mitarbeitern
    -0.83
     HDTV
    -0.82
    POSITIVE LOGITS
     practices
    1.13
     debates
    1.09
     spaces
    1.09
    imagined
    1.07
     elites
    1.05
     contextos
    1.05
     entangled
    1.05
     nineteenth
    1.04
     networks
    1.02
     circulation
    1.02
    Activations Density 0.084%

    No Known Activations