© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11323
    Prev
    Next
    INDEX
    Explanations

    information context

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

    The neuron fires strongly on instances of the word “information.”

    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
    y
    -3.44
    時間
    -2.92
    しっかり
    -2.86
     ouverture
    -2.69
    眼睛
    -2.66
     humeur
    -2.59
    老婆
    -2.58
    珵
    -2.58
    方法
    -2.56
    内容
    -2.56
    POSITIVE LOGITS
    .
    4.97
    弍
    3.69
    玧
    3.45
    轫
    3.05
    酝
    2.95
    誊
    2.88
    ஂ
    2.84
    汭
    2.84
    
    2.84
    趼
    2.81
    Activations Density 0.040%

    No Known Activations