© 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. 74105
    Prev
    Next
    INDEX
    Explanations

    disrupt; disruption; disruptive

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

    The neuron activates on various forms of the word “disrupt” (e.g., disrupt, disrupting, disruption, disruptors).

    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
    灕
    -1.80
    BESCHREIBUNG
    -1.70
    …」
    -1.70
     précie
    -1.57
    訣
    -1.53
     Besonders
    -1.52
    .“
    -1.51
     zufolge
    -1.50
    迄
    -1.46
    BIBLIO
    -1.45
    POSITIVE LOGITS
    \
    1.91
    </b>
    1.90
    <
    1.81
     \{
    1.62
     trends
    1.58
    $
    1.57
     in
    1.50
    \}
    1.50
     $\
    1.48
    factors
    1.45
    Activations Density 0.009%

    No Known Activations