© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69777
    Prev
    Next
    INDEX
    Explanations

    passage of objects or movement

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

    The neuron strongly activates on Portuguese infinitive verbs ending in “-ar.”

    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
    [
    -3.77
    {
    -3.36
    e
    -2.88
    (
    -2.86
    ↵↵
    -2.66
    -
    -2.63
    am
    -2.63
    d
    -2.59
    "
    -2.53
    il
    -2.44
    POSITIVE LOGITS
     They
    3.25
    咘
    2.75
     搞笑
    2.70
    摃
    2.67
     trattato
    2.66
     และ
    2.66
    蘩
    2.64
    乆
    2.64
    妡
    2.64
     mereka
    2.61
    Activations Density 0.003%

    No Known Activations