© 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. 6719
    Prev
    Next
    INDEX
    Explanations

    refused requests

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

    The neuron strongly lights up on unusually rare or “surprising” individual tokens—i.e. low‐frequency words or symbols that carry high information content.

    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
    خ
    0.79
     ر
    0.74
     То
    0.74
    ش
    0.73
    ون
    0.73
    ದ್
    0.70
    كو
    0.69
     방
    0.68
     supposition
    0.68
    وپ
    0.67
    POSITIVE LOGITS
     اتحاد
    0.84
     Yous
    0.83
    тные
    0.80
     Axes
    0.80
     Brahma
    0.79
    喈
    0.78
    cakes
    0.78
     Gummies
    0.77
    ้ำ
    0.75
    тных
    0.75
    Activations Density 0.000%

    No Known Activations