© 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. 116619
    Prev
    Next
    INDEX
    Explanations

    occurrences each year

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

    The neuron detects numeric-statistical expressions—counts, frequencies, and other quantified data 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
     اليوم
    -1.11
     quelconque
    -1.11
     dotyczące
    -1.00
    udnio
    -0.97
    Daily
    -0.96
    ╩
    -0.96
    .='
    -0.94
    ='';
    -0.92
    nitz
    -0.91
     tudo
    -0.91
    POSITIVE LOGITS
     each
    6.97
     every
    6.03
     chaque
    5.22
     setiap
    4.81
     jedes
    4.75
     annually
    4.69
     каждый
    4.56
     varje
    4.53
    Each
    4.47
     mỗi
    4.34
    Activations Density 0.228%

    No Known Activations