© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11618
    Prev
    Next
    INDEX
    Explanations

    CDR, Cod, CORD

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

    The neuron is essentially triggered by the two-letter acronyms “CD” or “DC” (e.g. in “CD quality,” “DC emulation,” etc.).

    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_31_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
    発展
    0.55
    太子
    0.54
     Pedersen
    0.54
     Nxc
    0.53
     ביק
    0.53
     gahet
    0.52
    穼
    0.52
     Toms
    0.51
    ऐ
    0.51
     péd
    0.50
    POSITIVE LOGITS
     CD
    0.65
    CD
    0.61
    omin
    0.57
    мия
    0.57
    zens
    0.57
     cd
    0.57
    rom
    0.55
    KT
    0.55
     Cd
    0.55
    條件
    0.55
    Activations Density 0.161%

    No Known Activations