© 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. 100962
    Prev
    Next
    INDEX
    Explanations

    suffix "-izing"

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

    The neuron fires on subword affixal endings (i.e. morphological suffixes) across different languages.

    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
     we
    -1.84
    B
    -1.82
    s
    -1.70
     '
    -1.66
    .'
    -1.66
    .\"
    -1.61
     réfugiés
    -1.59
    P
    -1.59
     that
    -1.54
     $<
    -1.54
    POSITIVE LOGITS
    榦
    1.97
    搋
    1.69
     Jugendliche
    1.66
    zarchiwizowane
    1.57
     Erwachsene
    1.45
    ipzig
    1.41
    iecie
    1.40
    
    1.40
     قوی
    1.40
    fgaben
    1.40
    Activations Density 0.002%

    No Known Activations