© 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. 22-GEMMASCOPE-RES-131K
    7. 27436
    Prev
    Next
    INDEX
    Explanations

    "It" followed by a verb

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

    This neuron strongly activates on the standalone pronoun “It” at the start of sentences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     just
    -1.38
     even
    -1.28
     for
    -1.17
     الصغيرة
    -1.13
    咐
    -1.09
    --,
    -1.09
     zahlreiche
    -1.07
    Вопрос
    -1.06
    了不少
    -1.06
    Даже
    -1.05
    POSITIVE LOGITS
     is
    1.61
     It
    1.44
     also
    1.20
     inoltre
    1.18
    hese
    1.11
     但是
    1.10
     najlepiej
    1.10
    
    1.10
    also
    1.09
     zui
    1.09
    Activations Density 0.118%

    No Known Activations