© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4397
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to Dutch adjectives ending in “-ig.”

    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
    uré
    0.59
    y
    0.53
     occurrences
    0.52
     leapt
    0.52
    people
    0.52
    asign
    0.52
    yay
    0.51
    cted
    0.51
    rames
    0.51
    ']]
    0.51
    POSITIVE LOGITS
    ของ
    0.68
    ของการ
    0.67
     vergleich
    0.65
     τους
    0.63
    ιο
    0.61
    នៃការ
    0.61
     langfrist
    0.61
     zien
    0.59
     της
    0.59
     dovr
    0.57
    Activations Density 0.000%

    No Known Activations