© 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. 54455
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

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

    The neuron strongly activates on personal subject pronouns (e.g. I, he/She/they, it) used as sentence subjects.

    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
     from
    -1.34
     What
    -1.32
     after
    -1.30
     sehr
    -1.27
     Using
    -1.27
    Some
    -1.23
     Before
    -1.23
    Using
    -1.22
    Before
    -1.22
    what
    -1.18
    POSITIVE LOGITS
     geladeira
    1.28
     namin
    1.23
     limpeza
    1.17
    Ȏ
    1.17
    哙
    1.16
    ㈰
    1.16
    肯定会
    1.14
     verschillende
    1.14
     ſol
    1.13
     ular
    1.13
    Activations Density 0.016%

    No Known Activations