© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11741
    Prev
    Next
    INDEX
    Explanations

    saving those records

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

    The neuron is detecting bibliography/references metadata (e.g. citation entries with author initials, paper titles, journal volume/pages, and numeric identifiers).

    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_24_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
    )$,
    0.85
    бы
    0.83
    был
    0.79
    ﺰ
    0.79
    ды
    0.77
    IBLE
    0.75
    ных
    0.74
    。)
    0.74
    ﺐ
    0.73
    ETIC
    0.73
    POSITIVE LOGITS
     britannique
    0.91
     arrondie
    0.82
     humili
    0.81
    마
    0.80
     matematica
    0.80
    まずは
    0.79
     difficultés
    0.79
     convexe
    0.78
     megt
    0.77
     milik
    0.76
    Activations Density 0.000%

    No Known Activations