© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1439
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

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

    The neuron strongly activates on common English personal pronouns (I, you, he, she, we, they, etc.).

    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
     by
    -2.34
     or
    -2.23
     only
    -2.17
     at
    -2.17
     using
    -2.16
     epitom
    -2.16
     ostensibly
    -2.14
     blatantly
    -2.14
     after
    -2.14
     as
    -2.14
    POSITIVE LOGITS
    킁
    2.09
     Dinas
    2.08
    commonly
    2.05
     .........
    2.00
     .......
    2.00
    ᕮ
    1.99
     prace
    1.98
    primarily
    1.97
    <0xF4>
    1.95
     dando
    1.95
    Activations Density 0.091%

    No Known Activations