© 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. 1924
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

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

    The neuron chiefly responds to numeric tokens (especially dates, years, and standalone numbers).

    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
     these
    0.64
     diese
    0.64
     THESE
    0.57
     THIS
    0.56
     MOQ
    0.56
     data
    0.55
     URI
    0.55
     p
    0.54
     IUCN
    0.54
     Google
    0.54
    POSITIVE LOGITS
    ulls
    0.70
     svou
    0.63
     తన
    0.63
     superstar
    0.60
     swoim
    0.60
     swoją
    0.59
     သူ့
    0.59
     beeindruck
    0.58
     najbol
    0.58
    笑着
    0.58
    Activations Density 0.021%

    No Known Activations