© 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. 105577
    Prev
    Next
    INDEX
    Explanations

    could not do

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

    The neuron is a strong detector for the word “not” (i.e. simple negation).

    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
     renown
    -2.59
    檍
    -2.28
     большин
    -2.19
    ᠌
    -2.17
    縠
    -2.16
    要不然
    -2.14
    ,”
    -2.11
     cohe
    -2.09
    ES
    -2.05
     véritable
    -2.05
    POSITIVE LOGITS
    ी
    2.19
    </td>
    2.19
     be
    2.05
    י
    2.05
     This
    1.96
    嵛
    1.95
    }{
    1.95
    
    1.94
     infarction
    1.93
     може
    1.90
    Activations Density 0.004%

    No Known Activations