© 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. 34-GEMMASCOPE-RES-131K
    7. 8462
    Prev
    Next
    INDEX
    Explanations

    first-person singular pronoun

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

    The neuron fires strongly on words and punctuation that occur inside quoted speech—i.e. it marks off direct quotations.

    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
    𝐢
    -1.90
    你就
    -1.75
     ندار
    -1.70
    你是不是
    -1.52
    那你
    -1.50
     xxiv
    -1.46
     esquer
    -1.45
     territo
    -1.45
    べし
    -1.44
    你说
    -1.43
    POSITIVE LOGITS
     I
    8.63
     אני
    3.81
     my
    3.77
     tôi
    3.70
    ผม
    3.23
     я
    3.20
     me
    2.92
     мне
    2.77
    私は
    2.75
     jsem
    2.66
    Activations Density 2.289%

    No Known Activations