© 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. 2222
    Prev
    Next
    INDEX
    Explanations

    's followed by a noun

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

    The neuron detects possessive markers (apostrophe-s) in words.

    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
    t
    0.85
    k
    0.79
    m
    0.74
    c
    0.74
    h
    0.71
    en
    0.71
    el
    0.69
    w
    0.66
    et
    0.65
    id
    0.64
    POSITIVE LOGITS
    ﺎ
    0.64
    制品
    0.63
    रसा
    0.57
    গ্রন্থ
    0.56
     informazioni
    0.55
    कारण
    0.55
    后再
    0.55
    ället
    0.54
     confectionery
    0.54
     Ví
    0.54
    Activations Density 0.052%

    No Known Activations