© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1690
    Prev
    Next
    INDEX
    Explanations

    pronoun usage (it, them)

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

    The neuron responds to tokens that occur at the very start of new sentences or list items.

    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
    い
    1.08
    и
    0.92
    ে
    0.87
    0
    0.85
    ת
    0.85
    ులు
    0.83
    ا
    0.82
    UU
    0.81
    U
    0.80
    у
    0.80
    POSITIVE LOGITS
     Põ
    0.77
    슘
    0.77
    theoretic
    0.75
    傈
    0.75
    ty
    0.73
    요
    0.71
     Pemer
    0.69
     Politicians
    0.68
    tting
    0.68
    बाबत
    0.68
    Activations Density 0.192%

    No Known Activations