© 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. 47850
    Prev
    Next
    INDEX
    Explanations

    introduction heading

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

    The neuron consistently activates on the word “Introduction” when it appears as a section heading.

    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
    O
    -3.30
    -
    -2.98
    =
    -2.97
    秾
    -2.88
    2
    -2.67
    ta
    -2.67
    >
    -2.66
    眼睛
    -2.63
    냑
    -2.58
        
    -2.55
    POSITIVE LOGITS
    姈
    3.42
    霂
    3.38
    鈊
    3.22
    摃
    3.19
    .
    3.09
    
    3.08
    骉
    2.95
    ⃜
    2.94
    最后由
    2.92
    猹
    2.83
    Activations Density 0.033%

    No Known Activations