© 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. 1535
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

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

    The neuron activates on numeric tokens—sequences of digits representing 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
     Pará
    -0.87
     five
    -0.80
     six
    -0.79
     transporta
    -0.75
     seven
    -0.73
     Français
    -0.71
    千年
    -0.69
     reliable
    -0.69
     stolet
    -0.69
    ماع
    -0.67
    POSITIVE LOGITS
    
    0.99
    ţe
    0.90
     {:.
    0.87
    ^.
    0.84
    Jedi
    0.82
     fabs
    0.82
    fabs
    0.80
    nyi
    0.80
     Banjo
    0.77
    __.
    0.77
    Activations Density 0.191%

    No Known Activations