© 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. 466
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

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

    The neuron activates on high‐frequency/common words (especially pronouns, auxiliaries, prepositions, and other very frequent tokens).

    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
     cabello
    -0.90
     currently
    -0.90
     klasy
    -0.89
     csak
    -0.84
    ða
    -0.83
    只
    -0.83
    currently
    -0.82
     нужно
    -0.82
     ۰
    -0.81
     тести
    -0.81
    POSITIVE LOGITS
     deput
    0.93
    ্ম
    0.91
    urgence
    0.85
    Komple
    0.85
    agosto
    0.85
     remain
    0.82
    Kako
    0.81
    ๊ะ
    0.81
     serde
    0.81
     マーク
    0.81
    Activations Density 0.032%

    No Known Activations