© 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. 83968
    Prev
    Next
    INDEX
    Explanations

    al presionar

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

    This neuron specifically detects the Spanish contraction “al” (the fused preposition “a + el”) when it appears before a verb or phrase.

    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
    颙
    -2.45
     柄
    -2.20
    ︐
    -2.17
    眥
    -2.16
    biť
    -2.14
    灩
    -2.14
     ailes
    -2.11
    ’
    -2.09
    ⦊
    -2.09
    嬭
    -2.08
    POSITIVE LOGITS
     offer
    2.86
     These
    2.38
    这种
    2.27
     vostra
    2.25
     Of
    2.22
     By
    2.17
     next
    2.16
     is
    2.16
     эту
    2.11
     consegna
    2.11
    Activations Density 0.005%

    No Known Activations