© 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. 66587
    Prev
    Next
    INDEX
    Explanations

    acknowledge what/that/the

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

    The neuron is tuned to spot the word “acknowledge” (and its inflected forms).

    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
    i
    -3.09
      
    -2.66
    </h1>
    -2.64
    a
    -2.55
     They
    -2.48
    of
    -2.47
     "
    -2.47
    </strong>
    -2.41
    </h3>
    -2.36
    癀
    -2.31
    POSITIVE LOGITS
    涐
    2.41
    䉴
    2.41
     dansk
    2.41
    茀
    2.41
    medriver
    2.22
    ♪♪
    2.14
     \&
    2.14
    ‪.‬‬
    2.09
    取决
    2.08
    年
    2.00
    Activations Density 0.005%

    No Known Activations