© 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. 29172
    Prev
    Next
    INDEX
    Explanations

    French "I"

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

    The neuron fires specifically on the token “je” (in its various capitalizations).

    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
    珰
    -2.73
    镡
    -2.72
    嗩
    -2.70
    ଃ
    -2.67
    ቍ
    -2.64
    釓
    -2.48
     baan
    -2.47
     panneaux
    -2.47
    呿
    -2.47
    变了
    -2.41
    POSITIVE LOGITS
    "
    2.94
     own
    2.88
    In
    2.77
     With
    2.41
    At
    2.36
     were
    2.33
     for
    2.31
    (
    2.27
     on
    2.25
    The
    2.17
    Activations Density 0.001%

    No Known Activations