© 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. 10-GEMMASCOPE-RES-131K
    7. 104848
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs

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

    The neuron strongly responds to first-person pronouns (e.g. “I,” “we”) indicating the speaker’s own statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    quelize
    -1.55
    ądze
    -1.52
     létre
    -1.47
    囿
    -1.47
     gewiß
    -1.46
    eração
    -1.45
     Arzneimit
    -1.43
     barvy
    -1.42
     maceta
    -1.42
     andern
    -1.42
    POSITIVE LOGITS
     to
    1.85
    🩹
    1.48
    できるので
    1.44
     tecnologie
    1.33
    场面
    1.28
     such
    1.27
    ofed
    1.27
    êle
    1.27
    多么
    1.26
    Various
    1.23
    Activations Density 0.156%

    No Known Activations