© 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. 10-GEMMASCOPE-RES-131K
    7. 101425
    Prev
    Next
    INDEX
    Explanations

    acting quietly or secretly

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

    The neuron activates on adverbs that signal low-key or unobtrusive action (e.g., “quietly,” “silently”).

    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
    ↵↵
    -2.80
    {
    -2.39
            
    -1.98
    V
    -1.95
    T
    -1.92
    S
    -1.91
     adorable
    -1.84
     nominally
    -1.80
    E
    -1.79
     &
    -1.76
    POSITIVE LOGITS
    嗵
    2.44
    寕
    2.39
     撮っ
    2.39
     広場
    2.38
     水彩
    2.20
     parachoque
    2.17
    縢
    2.14
    鹮
    2.11
     tramontina
    2.05
    佧
    2.03
    Activations Density 0.004%

    No Known Activations