© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6605
    Prev
    Next
    INDEX
    Explanations

    expert in a role

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

    The neuron fires on occurrences of the word “Expert,” marking expert‐attributed answers.

    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
     ›
    0.65
    ISTA
    0.60
     било
    0.59
    マス
    0.58
     MHz
    0.57
    UTES
    0.57
     APK
    0.57
     Dimensions
    0.55
    繍
    0.55
     Bout
    0.54
    POSITIVE LOGITS
    ]।
    0.57
    ==========
    0.55
    inae
    0.55
    可以看到
    0.54
     cubierta
    0.53
     nadzie
    0.52
     کی۔
    0.52
    有机会
    0.52
     incon
    0.51
    achable
    0.51
    Activations Density 0.002%

    No Known Activations