© 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. 91879
    Prev
    Next
    INDEX
    Explanations

    patent application numbers

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

    The neuron activates on standalone numeric tokens—especially multi‐digit sequences such as years, patent or case numbers, scores, etc.

    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
     отече
    -0.75
    thical
    -0.74
     cape
    -0.73
    
    -0.73
    gee
    -0.71
    Sair
    -0.71
    Templates
    -0.70
    //(
    -0.69
    ">-
    -0.69
    více
    -0.69
    POSITIVE LOGITS
    దు
    0.83
     鸟
    0.74
    長男
    0.73
    WebApplication
    0.72
    sibirsk
    0.71
    acken
    0.70
    sibilità
    0.69
     vantaggio
    0.69
     attention
    0.68
    tora
    0.68
    Activations Density 0.004%

    No Known Activations