© 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. 66011
    Prev
    Next
    INDEX
    Explanations

    thrown with prepositions

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

    This neuron detects occurrences of the past-participle verb “thrown.”

    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
    呖
    -3.39
    или
    -2.73
     یا
    -2.72
    昃
    -2.69
     atau
    -2.67
     dicendo
    -2.64
     или
    -2.61
     尔
    -2.53
    褔
    -2.52
    c
    -2.50
    POSITIVE LOGITS
    淠
    3.66
     technisch
    2.91
     verminder
    2.83
    翾
    2.78
     altamente
    2.66
    があり
    2.64
    ፨
    2.59
     rechte
    2.58
    骉
    2.58
     bedien
    2.50
    Activations Density 0.001%

    No Known Activations