© 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. 22-GEMMASCOPE-RES-131K
    7. 38693
    Prev
    Next
    INDEX
    Explanations

    javascript code

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

    The neuron fires on numeric literals (multi‐digit numbers) appearing in the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    更是
    -0.95
    ↵
    -0.91
     his
    -0.90
     对
    -0.89
    支持
    -0.83
     weltweit
    -0.83
    しまいます
    -0.82
     așa
    -0.82
     första
    -0.82
     reloadData
    -0.82
    POSITIVE LOGITS
    mmation
    1.17
    izacin
    1.14
    っております
    1.14
    heses
    1.13
     сс
    1.03
     signifikan
    1.03
    rdoba
    1.02
    membered
    1.02
     aras
    1.02
    ございました
    1.02
    Activations Density 0.001%

    No Known Activations