© 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. 7592
    Prev
    Next
    INDEX
    Explanations

    two options, risk, damage, machines

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

    The neuron fires on extended, formal how-to or advice passages about setting up and running a small or online business.

    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
     ۽
    0.29
     ਅਤੇ
    0.27
     Mereka
    0.26
     आणि
    0.26
     एवं
    0.26
    ␊
    0.25
    ௭
    0.25
    ⊡
    0.25
     અને
    0.24
    átiles
    0.24
    POSITIVE LOGITS
    handed
    0.26
    দেখে
    0.25
     rigorous
    0.24
     haus
    0.23
     affective
    0.23
     floppy
    0.23
     handful
    0.23
     emphatic
    0.23
    いただ
    0.22
    fallen
    0.22
    Activations Density 0.002%

    No Known Activations