© 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. 69338
    Prev
    Next
    INDEX
    Explanations

    didn't + expect/do

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

    The neuron strongly activates on the “’t” token in negative contractions (e.g. didn’t, don’t, won’t), effectively spotting negation endings.

    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
     algunas
    -1.64
     alcuni
    -1.51
     einigen
    -1.47
     algunos
    -1.46
    的一些
    -1.45
     diğer
    -1.45
     our
    -1.43
     wielu
    -1.43
     some
    -1.43
     alcune
    -1.42
    POSITIVE LOGITS
     have
    1.99
     viewDidLoad
    1.52
    䊉
    1.52
    quium
    1.46
     know
    1.45
    beforeAll
    1.45
    hoka
    1.43
     Metern
    1.41
    stered
    1.38
     "";
    1.38
    Activations Density 0.024%

    No Known Activations