© 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. 6400
    Prev
    Next
    INDEX
    Explanations

    possessive determiners followed by own

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

    The neuron fires on words that signal personal ownership or background (e.g. own, research, heritage).

    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
    '],
    0.75
    та
    0.73
    的要求
    0.71
    '];
    0.70
    `](
    0.68
    '].
    0.67
    ம்
    0.65
     CGRectMake
    0.65
    ruptcy
    0.64
     restantes
    0.64
    POSITIVE LOGITS
     own
    1.28
     propios
    0.99
     propias
    0.96
     propio
    0.95
     wits
    0.93
     própria
    0.93
    ি
    0.90
     próprio
    0.89
     propia
    0.86
    י
    0.83
    Activations Density 0.294%

    No Known Activations