© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117054
    Prev
    Next
    INDEX
    Explanations

    documentation and code structure

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

    This neuron is specialized for spotting numeric tokens (i.e. sequences of digits) 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
    lists
    -0.70
    待つ
    -0.65
    lista
    -0.64
     حمل
    -0.64
    LIST
    -0.64
     Traverse
    -0.63
    ("-");
    -0.63
    箩
    -0.63
     embassy
    -0.62
     Embassy
    -0.62
    POSITIVE LOGITS
    
    0.72
     الدول
    0.68
     pusi
    0.65
     darstellen
    0.63
    BIE
    0.63
    沌
    0.62
     Sancho
    0.61
     AUSSI
    0.60
     Receipt
    0.60
    ISK
    0.60
    Activations Density 0.087%

    No Known Activations