© 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. 6802
    Prev
    Next
    INDEX
    Explanations

    showing or listing

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

    The neuron fires on Romance‐language conjugations of the verb “to show” (e.g. Spanish/Portuguese forms like muestra, mostrar, mostrando).

    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
    ſſen
    -2.69
    鋱
    -2.58
    呖
    -2.52
    푆
    -2.39
    鯪
    -2.38
    考试
    -2.34
    ଝ
    -2.33
    銪
    -2.31
     barca
    -2.30
    グルト
    -2.27
    POSITIVE LOGITS
    .
    3.17
    …….
    2.67
    It
    2.64
     —
    2.61
     “
    2.48
     Then
    2.47
     gemeinsame
    2.36
     redução
    2.36
    ..........
    2.31
    They
    2.30
    Activations Density 0.001%

    No Known Activations