© 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. 10588
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives

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

    This neuron detects English contractions—words with apostrophes like ’s, ’d, ’ll, ’m, 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
    .
    -2.17
     favorece
    -1.80
     it
    -1.63
     zawsze
    -1.63
     verschillen
    -1.63
     aconte
    -1.60
     continuará
    -1.54
    もありました
    -1.54
    當時
    -1.53
    他們
    -1.52
    POSITIVE LOGITS
     to
    1.77
    S
    1.67
    orithm
    1.62
     و
    1.61
    BoxShadow
    1.60
    $}
    1.56
    %),
    1.52
    itemBuilder
    1.51
    medades
    1.49
    titudes
    1.47
    Activations Density 0.006%

    No Known Activations