© 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. 34-GEMMASCOPE-RES-131K
    7. 108398
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

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

    The neuron strongly activates on past-tense and past-participle verb forms (e.g. words ending in –ed, –en, or –ized).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Took
    -1.01
     была
    -0.98
     grew
    -0.90
     Wettbewerb
    -0.90
    Răsp
    -0.90
     blew
    -0.89
     wrote
    -0.85
     воспользоваться
    -0.85
     chose
    -0.83
    試試
    -0.83
    POSITIVE LOGITS
    ized
    2.27
    ed
    2.02
    ated
    2.00
    ted
    1.88
    ulated
    1.73
    ened
    1.70
     شده
    1.67
    ned
    1.62
    tituted
    1.55
    ded
    1.54
    Activations Density 0.196%

    No Known Activations