© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73890
    Prev
    Next
    INDEX
    Explanations

    it was

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

    This neuron responds to 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_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
    なお
    -1.20
     なお
    -1.08
    ユーザ
    -1.08
     bucal
    -1.08
    agora
    -1.05
    ина
    -1.02
    RESUMO
    -1.02
    ствии
    -1.02
    的笑容
    -1.02
    Ahora
    -1.02
    POSITIVE LOGITS
     [
    1.55
    Kenapa
    1.33
     different
    1.29
     väldigt
    1.24
     like
    1.23
    Kelebihan
    1.20
     there
    1.17
     mutta
    1.13
    Bukan
    1.13
    Kondisi
    1.12
    Activations Density 0.008%

    No Known Activations