© 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. 6192
    Prev
    Next
    INDEX
    Explanations

    env python

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

    The neuron fires on bibliographic‐style metadata tokens—things like DOIs, volume/page numbers, dates, and other citation or reference identifiers.

    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
    вір
    0.82
     particolarmente
    0.81
     comportamenti
    0.77
    ві
    0.76
     particolari
    0.75
    ґ
    0.74
     зокрема
    0.73
    ocular
    0.72
    ب
    0.72
    aments
    0.70
    POSITIVE LOGITS
    klassen
    0.85
     kall
    0.84
     mies
    0.82
     Classe
    0.79
    sf
    0.79
     merk
    0.79
     klasse
    0.79
     Kone
    0.77
    CHS
    0.76
     CIM
    0.75
    Activations Density 0.000%

    No Known Activations