© 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. 14022
    Prev
    Next
    INDEX
    Explanations

    this show on the road, wish to ask

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

    The neuron fires on mentions of toilet paper (bathroom tissue) products.

    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
    ushing
    0.82
    čna
    0.82
    鋤
    0.82
    ētu
    0.81
    aupun
    0.81
    ‟
    0.80
    みに
    0.80
    сную
    0.79
    ulle
    0.79
    čkom
    0.78
    POSITIVE LOGITS
    噗
    0.70
    RELL
    0.69
     וכ
    0.67
    Classpath
    0.66
     лига
    0.65
     править
    0.64
    Characteristic
    0.64
    Variable
    0.63
    Genres
    0.62
    Amount
    0.62
    Activations Density 0.003%

    No Known Activations