© 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. 59865
    Prev
    Next
    INDEX
    Explanations

    university president

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens (e.g. digits, scores, rankings, dates), effectively detecting numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     toujours
    -0.87
     répondit
    -0.85
    斯
    -0.83
    пр
    -0.81
    urte
    -0.81
    Ako
    -0.81
    СТИ
    -0.79
     adelante
    -0.79
    都是
    -0.79
     Pradesh
    -0.78
    POSITIVE LOGITS
    “[
    0.98
    Colleg
    0.93
     “[
    0.90
    __["
    0.85
     Hệ
    0.81
     campus
    0.79
    "[
    0.77
    
    0.76
     university
    0.75
     GRAPH
    0.75
    Activations Density 0.006%

    No Known Activations