© 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. 68933
    Prev
    Next
    INDEX
    Explanations

    comprehension or lack thereof

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

    The neuron primarily detects occurrences of the word “understand” (and its morphological variants).

    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
     It
    -2.17
     The
    -2.00
     And
    -1.91
     it
    -1.89
     They
    -1.80
     a
    -1.79
     That
    -1.79
     With
    -1.65
     Such
    -1.63
     I
    -1.58
    POSITIVE LOGITS
     that
    2.33
    U
    1.98
    鬭
    1.81
    O
    1.73
    縲
    1.73
    ᷆
    1.71
     how
    1.71
    ING
    1.69
    没什么
    1.65
     Hvor
    1.63
    Activations Density 0.026%

    No Known Activations