© 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. 7267
    Prev
    Next
    INDEX
    Explanations

    plug.based onspace totracking *

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

    This neuron strongly activates on personal pronouns (especially first‐ and second‐person “I,” “we,” “me,” “you,” “my,” etc.).

    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
     (
    1.21
     “
    1.21
     "
    1.20
    （
    1.02
    0.94
     multi
    0.92
    (
    0.91
     '
    0.90
     ‘
    0.89
     in
    0.87
    POSITIVE LOGITS
     เอ่อ
    1.16
     вашего
    1.12
     вашу
    1.08
     ваше
    1.05
     ваших
    1.04
     よろしく
    1.03
    ໋
    1.03
     вашей
    1.02
     моего
    0.99
    𝓐
    0.99
    Activations Density 0.343%

    No Known Activations