© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112507
    Prev
    Next
    INDEX
    Explanations

    reign

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

    The neuron activates specifically on occurrences of the string “reign” (e.g. “reigning,” “reign”) in various forms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    geſ
    -2.67
    鹇
    -2.47
    一来
    -2.39
    ᐕ
    -2.34
    悭
    -2.30
    愠
    -2.28
    ⢧
    -2.28
    臯
    -2.27
     falsely
    -2.25
     ignite
    -2.25
    POSITIVE LOGITS
    ,
    2.48
    
    2.28
    selbe
    2.22
    E
    2.22
    A
    2.09
    K
    2.08
    क्टर
    2.05
    
    2.02
    地元
    1.99
    ྂ
    1.95
    Activations Density 0.003%

    No Known Activations