© 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. 61259
    Prev
    Next
    INDEX
    Explanations

    it refers to

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

    The neuron consistently activates on occurrences of the pronoun “it.”

    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
    -1.87
    .
    -1.55
     __
    -1.39
    -1.39
     heilig
    -1.32
    “
    -1.31
     stille
    -1.30
     еще
    -1.30
     <
    -1.30
     noch
    -1.27
    POSITIVE LOGITS
     育
    1.46
     Pristup
    1.42
     dianggap
    1.37
     eight
    1.37
     darbo
    1.36
    érales
    1.34
     komunikasi
    1.32
    壜
    1.32
    お得
    1.30
    These
    1.30
    Activations Density 0.056%

    No Known Activations