© 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. 65486
    Prev
    Next
    INDEX
    Explanations

    involvement

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

    The neuron fires strongly on the word “involvement,” especially in contexts like “involvement of,” flagging occurrences of that specific term.

    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
    There
    -3.17
    方法
    -3.06
    しっかり
    -2.97
    x
    -2.95
    When
    -2.89
    With
    -2.89
     There
    -2.86
    长
    -2.81
    時間
    -2.81
    end
    -2.81
    POSITIVE LOGITS
    趼
    4.16
    
    3.53
    汭
    3.31
    姈
    3.19
    
    3.06
    ፨
    3.00
    𐄁
    2.97
    
    2.95
    弍
    2.89
    ☫
    2.88
    Activations Density 0.004%

    No Known Activations