© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6149
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

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

    The neuron is detecting third-person male pronouns (e.g. “He,” “he,” “His”) in narrative text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    0.94
    y
    0.73
    ;
    0.72
    u
    0.71
    }.
    0.70
    }:
    0.68
    }$.
    0.67
    il
    0.66
    :+
    0.64
    ilgan
    0.63
    POSITIVE LOGITS
     сказал
    0.87
    他们
    0.75
    是他
    0.75
    iobium
    0.75
    тельно
    0.74
    ಾತ
    0.74
    是个
    0.73
    たちが
    0.73
     nacido
    0.72
     ပြော
    0.71
    Activations Density 0.108%

    No Known Activations