© 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. 56094
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation followed by words

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

    The neuron fires on numeric tokens (numbers).

    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
    Kaj
    -0.98
    Ecuador
    -0.94
    bardier
    -0.92
    Monsieur
    -0.90
    EXHIB
    -0.89
     Gucci
    -0.88
     समस्या
    -0.87
    Sylvie
    -0.87
    Thierry
    -0.87
    NANCY
    -0.86
    POSITIVE LOGITS
    "),
    0.91
    .*;
    0.90
     Serien
    0.89
    [];
    0.89
    _;
    0.89
    "):
    0.89
    чали
    0.88
    package
    0.88
     総合
    0.88
    шир
    0.87
    Activations Density 0.023%

    No Known Activations