© 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. 12676
    Prev
    Next
    INDEX
    Explanations

    negation and punctuation

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

    The neuron is strongly activated by common function words—especially short pronouns, articles, copulas, and modals (e.g. “a,” “it,” “is,” “may,” “be,” “I,” “but,” “no,” etc.).

    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
    rechter
    -1.55
     rése
    -1.52
    ଃ
    -1.52
    
    -1.52
    ïn
    -1.51
     RESULT
    -1.49
    
    -1.49
    RTCF
    -1.48
    鹛
    -1.48
    繍
    -1.48
    POSITIVE LOGITS
     not
    1.97
    "
    1.84
    ?
    1.67
     Not
    1.63
     
    1.61
    =
    1.59
    !
    1.59
    In
    1.58
    —
    1.55
    :
    1.53
    Activations Density 0.016%

    No Known Activations