© 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. 12435
    Prev
    Next
    INDEX
    Explanations

    following punctuation

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

    The neuron flags instructional or explanatory text—i.e. tutorial‐style, how-to or educational passages.

    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
     intricately
    0.79
     captivating
    0.78
     artistry
    0.74
    ✨
    0.74
     undeniably
    0.72
    🌟
    0.72
     vibrancy
    0.71
     impactful
    0.70
    regarding
    0.69
    🛡
    0.69
    POSITIVE LOGITS
     Bf
    0.73
     Vf
    0.71
     Producto
    0.71
     onem
    0.67
     Zanu
    0.66
     anaknya
    0.65
     objetivo
    0.65
     örg
    0.64
     zuerst
    0.62
     WW
    0.61
    Activations Density 0.005%

    No Known Activations