© 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. 49099
    Prev
    Next
    INDEX
    Explanations

    Submitted legal documents

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

    The neuron activates on numeric tokens (digits, version numbers, counts, dates, etc.) 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
     element
    -0.80
     Schuld
    -0.74
    Hvad
    -0.71
    Ros
    -0.70
     guess
    -0.69
     элемент
    -0.69
     Ros
    -0.69
    udert
    -0.69
     nghĩa
    -0.68
    occur
    -0.68
    POSITIVE LOGITS
    liders
    0.73
    isamment
    0.72
     показа
    0.66
     decathlon
    0.65
     whiskers
    0.65
     deodorant
    0.62
     Seiko
    0.62
     metallurgy
    0.61
     advisable
    0.61
     Tutorials
    0.61
    Activations Density 0.044%

    No Known Activations