© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86720
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and subsequent prepositions

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

    The neuron primarily activates on past-tense verbs (both regular –ed forms and irregular past forms) describing events.

    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
    确实
    -1.47
    依旧
    -1.46
     eenig
    -1.40
     groote
    -1.40
    rinology
    -1.39
     aparentemente
    -1.38
     hemd
    -1.35
     hunne
    -1.34
     eenen
    -1.34
    anstal
    -1.34
    POSITIVE LOGITS
     my
    2.81
     our
    1.84
     by
    1.35
     over
    1.33
     even
    1.31
     every
    1.26
     We
    1.23
     before
    1.22
     Before
    1.17
    ന്റെ
    1.17
    Activations Density 0.109%

    No Known Activations