© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118714
    Prev
    Next
    INDEX
    Explanations

    expressing personal opinions and predictions

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

    The neuron fires on first-person self-references (e.g. “I,” “my,” “I’m,” “have” when used in personal statements).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    studies
    -1.06
     encant
    -1.05
    壕
    -0.99
    Opere
    -0.94
    lorin
    -0.93
    certificate
    -0.90
    SanPham
    -0.90
    了出去
    -0.90
    క్క
    -0.86
    zzet
    -0.85
    POSITIVE LOGITS
     still
    1.16
     predicting
    1.06
     also
    1.01
     esperaba
    0.97
     Predictions
    0.97
     always
    0.96
     expecting
    0.96
     predict
    0.94
     predicted
    0.91
     wasn
    0.90
    Activations Density 0.027%

    No Known Activations