© 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. 9937
    Prev
    Next
    INDEX
    Explanations

    g words

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

    The neuron strongly activates on capitalized tokens that are personal names—particularly surnames or author names in lists of contributors or citations.

    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
     thiết
    0.63
     בת
    0.61
    isième
    0.59
     코로나
    0.59
    廁
    0.56
     بالط
    0.55
    本社
    0.55
    ਕ
    0.55
    אים
    0.55
     표시
    0.55
    POSITIVE LOGITS
     giống
    0.98
     gorgeous
    0.91
     giá
    0.89
     जगह
    0.82
     громадян
    0.80
    gmail
    0.80
     gagal
    0.79
     garantire
    0.79
     gì
    0.78
     جنوب
    0.78
    Activations Density 1.903%

    No Known Activations