© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15632
    Prev
    Next
    INDEX
    Explanations

    list item indicator

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

    The neuron is strongly activated by citation‐style metadata—i.e. bracketed references, titles, authors, years, volume/page numbers—essentially bibliographic entries.

    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
     Seguridad
    0.63
     Produto
    0.56
     路
    0.54
     Ã
    0.53
     Klinik
    0.51
     집
    0.51
     类型
    0.51
     Spiel
    0.50
     مفت
    0.50
    栘
    0.50
    POSITIVE LOGITS
    ）、
    0.71
    ુર
    0.62
    ｂ
    0.61
     july
    0.60
    ）・
    0.59
    english
    0.59
     english
    0.58
    ༥
    0.58
    ｰ
    0.58
    ），
    0.57
    Activations Density 0.141%

    No Known Activations