© 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. 22-GEMMASCOPE-RES-131K
    4. 73645
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    The neuron primarily detects numeric expressions—quantities, measurements, and statistical values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ''
    
    -1.00
    竟然是
    -0.96
     interessa
    -0.96
    CONCLUSIONES
    -0.95
     ของ
    -0.95
    çoivent
    -0.94
     Distribu
    -0.94
     място
    -0.94
     optik
    -0.94
     Mississauga
    -0.92
    POSITIVE LOGITS
    ;
    1.03
     +
    0.93
    ALWAYS
    0.92
    Touch
    0.90
     घर
    0.90
     amable
    0.90
     otro
    0.89
     pop
    0.88
     aesthetics
    0.88
     Another
    0.84
    Activations Density 0.097%

    No Known Activations