© 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. 31-GEMMASCOPE-2-RES-16K
    7. 380
    Prev
    Next
    INDEX
    Explanations

    my purpose or programming

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

    The neuron activates on possessive determiners (e.g. “my,” “her,” “their,” “our”) indicating ownership or affiliation.

    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_31_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
    。
    0.29
     Again
    0.27
     Atau
    0.26
     ck
    0.25
     {
    0.25
    {
    0.25
    AndDelete
    0.24
     hoặc
    0.24
    ”。
    0.24
     &$\
    0.24
    POSITIVE LOGITS
     efforts
    0.49
     foray
    0.44
     inability
    0.43
     eagerness
    0.43
     penchant
    0.43
     ability
    0.41
     optimism
    0.41
     esfuerzos
    0.41
     unwillingness
    0.41
     commitment
    0.41
    Activations Density 1.367%

    No Known Activations