© 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. 12649
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by action or verb

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

    The main thing this neuron does is spot narrative reporting verbs that convey a character’s speech, thought, or internal feeling.

    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
     during
    0.98
     lors
    0.80
    during
    0.77
     Leute
    0.77
     durante
    0.76
     smacked
    0.74
    诟
    0.73
    期间
    0.73
     chatted
    0.73
     tijdens
    0.71
    POSITIVE LOGITS
    まずは
    0.87
    早速
    0.87
     forthwith
    0.84
     aussitôt
    0.80
     immediatamente
    0.80
     segera
    0.79
     instinctively
    0.79
     রওনা
    0.78
     hasten
    0.76
     দ্রুত
    0.75
    Activations Density 0.679%

    No Known Activations