© 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. 5693
    Prev
    Next
    INDEX
    Explanations

    vision techniques

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

    The neuron strongly activates on words that appear immediately after a sentence (or block) boundary—i.e. the first content token at the start of a sentence.

    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
    нг
    0.99
    ных
    0.88
     НА
    0.86
    ны
    0.83
     инициа
    0.83
    yana
    0.83
    т
    0.83
    ة
    0.82
     denominado
    0.82
    ра
    0.80
    POSITIVE LOGITS
    dine
    0.72
     Avalon
    0.71
    影像
    0.68
     intermission
    0.68
     propriety
    0.67
    idel
    0.66
    jenigen
    0.65
     Associate
    0.64
     Hubble
    0.64
     Intell
    0.64
    Activations Density 0.001%

    No Known Activations