© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 2923
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on personal subject pronouns (e.g. “you,” “he,” “I,” “it”) used to mark who’s performing or experiencing the action.

    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
     ,
    0.98
     /
    0.84
     :
    0.80
    ,.
    0.80
    ic
    0.79
     or
    0.79
     (
    0.78
    ar
    0.78
    ,"
    0.78
     ،
    0.78
    POSITIVE LOGITS
    想要的
    1.16
     möchte
    1.07
    could
    1.05
    想要
    1.02
    Само
    0.97
    Universidad
    0.96
    cannot
    0.96
     Enseñanza
    0.96
    Telefono
    0.95
     Органи
    0.95
    Activations Density 1.026%

    No Known Activations