© 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. 10639
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized to pick out numeric reference identifiers—floating-point numbers such as DOI or citation codes.

    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
    र
    0.70
    德國
    0.68
    पेक्षा
    0.68
     AdapterView
    0.66
     আট
    0.65
    E
    0.65
     systèmes
    0.64
    友人
    0.64
    ہ
    0.64
    成分
    0.63
    POSITIVE LOGITS
    ชร์
    0.89
    BSITE
    0.79
    dach
    0.79
    shint
    0.78
     грошы
    0.78
    โมง
    0.77
    loon
    0.77
    resto
    0.77
    ѝ
    0.77
    )}]
    0.76
    Activations Density 0.000%

    No Known Activations