© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10820
    Prev
    Next
    INDEX
    Explanations

    dangerous and wrong

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

    The neuron fires strongly at the start of each new paragraph or section, i.e. it identifies paragraph/section boundaries.

    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
     destacado
    0.91
     skilful
    0.91
     возникновения
    0.91
    เห็น
    0.90
    評判
    0.85
    快適
    0.81
     personalise
    0.81
    鷺
    0.80
     desenvolver
    0.80
     heighten
    0.79
    POSITIVE LOGITS
     pétales
    0.91
     précédentes
    0.80
     États
    0.75
     précédente
    0.74
     dernières
    0.72
     Ephesians
    0.72
    ğı
    0.70
    illä
    0.65
     apocalypse
    0.65
     sera
    0.64
    Activations Density 0.000%

    No Known Activations