© 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. 2719
    Prev
    Next
    INDEX
    Explanations

    roles and pronouns

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

    This neuron fires on third-person singular pronouns (he, him, her, it) in running 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
    0.90
     a
    0.82
     the
    0.73
    -
    0.70
     an
    0.65
     d
    0.65
     а
    0.61
     [
    0.59
     primary
    0.57
     en
    0.57
    POSITIVE LOGITS
    Jogador
    0.63
    Temperatura
    0.63
     Viên
    0.62
    goài
    0.61
    ărat
    0.59
    泬
    0.59
    汅
    0.59
    ckså
    0.58
    řízení
    0.58
    rilor
    0.58
    Activations Density 0.000%

    No Known Activations