© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103090
    Prev
    Next
    INDEX
    Explanations

    em programming contexts

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

    the Portuguese word "em" (meaning "in" or "on").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on the Portuguese preposition “em,” i.e. the token “em” (including capitalized “Em”).

    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
    ’
    -3.27
    to
    -2.86
     {
    -2.78
    "
    -2.75
    ;
    
    -2.64
    a
    -2.58
    er
    -2.47
    after
    -2.39
     remainder
    -2.38
     smallest
    -2.38
    POSITIVE LOGITS
    噲
    2.83
    ௅
    2.81
     ſta
    2.73
     valentín
    2.72
    棪
    2.53
    –¿
    2.53
    转头
    2.44
    趼
    2.42
    OUTUBE
    2.39
    盌
    2.39
    Activations Density 0.002%

    No Known Activations