© 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. 13046
    Prev
    Next
    INDEX
    Explanations

    log sigmoid completion

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

    This neuron fires most strongly on tokens that start a new 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
    fondo
    1.05
     iniziare
    0.94
    ד
    0.94
    ע
    0.91
    ggere
    0.86
    f
    0.80
    わた
    0.79
    К
    0.79
    Если
    0.77
    Excelente
    0.77
    POSITIVE LOGITS
     Constantine
    0.80
     Constant
    0.79
     Osw
    0.75
     MOU
    0.73
     Markham
    0.73
    騨
    0.71
     Rés
    0.71
     Kingsley
    0.70
     Taxonomy
    0.69
     وهنا
    0.68
    Activations Density 0.000%

    No Known Activations