© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38462
    Prev
    Next
    INDEX
    Explanations

    match any

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

    The neuron is detecting the “es” suffix that marks plural or word-ending “es.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    了一个
    -1.95
    厠
    -1.91
    笮
    -1.90
    !!,
    -1.89
     espectacular
    -1.88
    ציה
    -1.88
    anía
    -1.80
    atuur
    -1.75
    --"
    -1.73
     forment
    -1.73
    POSITIVE LOGITS
     to
    2.64
     или
    2.20
    ３
    2.02
     It
    1.82
     또는
    1.79
    _
    1.77
    หรือ
    1.77
     that
    1.72
     если
    1.71
    」，
    1.70
    Activations Density 0.053%

    No Known Activations