© 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. 10217
    Prev
    Next
    INDEX
    Explanations

    The neuron chiefly fires on salient content nouns—especially proper names, technical or thematic terms—distinguishing them from common function 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
     ανθρώ
    0.99
    pé
    0.88
    ்கு
    0.81
     ด่า
    0.80
    parentElement
    0.79
     homic
    0.79
    ጀ
    0.78
     hypertensive
    0.77
    )`,
    0.77
    ută
    0.77
    POSITIVE LOGITS
     모양
    1.00
    型的
    0.97
     shaped
    0.96
    형
    0.96
    般的
    0.91
    ．
    0.90
    shaped
    0.89
    cheerful
    0.89
     Ajouter
    0.89
    or
    0.88
    Activations Density 4.477%

    No Known Activations