© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6909
    Prev
    Next
    INDEX
    Explanations

    The neuron detects tokens that begin new sentences or sections (i.e. sentence-initial words).

    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
    i
    0.81
    iya
    0.77
     Некоторые
    0.75
    ak
    0.75
    ean
    0.75
    下一步
    0.74
    g
    0.73
    ians
    0.73
    ှ
    0.72
    橥
    0.72
    POSITIVE LOGITS
     vaginal
    0.83
     colle
    0.82
     intellig
    0.81
     maggiore
    0.81
     illuminate
    0.79
     exfoliating
    0.79
     malattia
    0.77
     giorno
    0.77
     queste
    0.77
     adjuvant
    0.77
    Activations Density 0.000%

    No Known Activations