© 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. 5354
    Prev
    Next
    INDEX
    Explanations

    classic, standard, common qualities

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

    The neuron strongly activates on mentions of “professional,” essentially picking up recommendations to hire or use a professional service.

    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
    ン
    0.77
    0.75
     მე
    0.68
    ن
    0.66
    ViewModel
    0.64
    ől
    0.62
    Id
    0.61
    คือ
    0.61
    AILED
    0.60
    U
    0.60
    POSITIVE LOGITS
    ৪৭
    0.63
    <unused2148>
    0.63
     mollus
    0.56
     обеспечить
    0.55
     hark
    0.55
     sensibilities
    0.55
     with
    0.52
    化的
    0.51
     येथील
    0.51
     पद्धतीने
    0.51
    Activations Density 0.003%

    No Known Activations