© 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. 8889
    Prev
    Next
    INDEX
    Explanations

    list item markers and structure

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

    This neuron detects numeric tokens and punctuation typical of bibliographic references (e.g. years, page and volume numbers, “html,” commas, and periods).

    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
    Market
    0.66
     функциони
    0.63
    👶
    0.63
     thất
    0.62
    ɵ
    0.61
    Kum
    0.61
     pensamiento
    0.59
     рынке
    0.59
     funcionamiento
    0.58
    
    0.58
    POSITIVE LOGITS
     perturbative
    0.81
     dynamical
    0.76
     Drinfeld
    0.76
     fermionic
    0.76
     arXiv
    0.71
     Dynamical
    0.70
     extremal
    0.66
     eigens
    0.66
    dynamical
    0.66
     Riemannian
    0.66
    Activations Density 0.042%

    No Known Activations