© 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. 66174
    Prev
    Next
    INDEX
    Explanations

    use in articles or documents

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

    The neuron is triggered by numeric references—years, dates, page or section numbers, counts, etc.—in running 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_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
    poptosis
    -1.01
    を中心に
    -0.99
     gastron
    -0.98
     جلسه
    -0.96
    ваться
    -0.96
    ayet
    -0.94
     campesinos
    -0.93
     brillant
    -0.93
     otak
    -0.93
     cartes
    -0.92
    POSITIVE LOGITS
     besø
    1.44
     usage
    1.29
     use
    1.29
    用例
    1.26
    During
    1.26
     used
    1.22
     uses
    1.22
     in
    1.22
    使用
    1.21
     erwähnten
    1.15
    Activations Density 0.055%

    No Known Activations