© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1957
    Prev
    Next
    INDEX
    Explanations

    information and data processing

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

    The neuron is triggered by references to data‐centric operations—terms like “data,” “analytics,” “processing,” and similar technical data‐management language.

    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
     yearling
    0.80
     sacrament
    0.75
    你自己
    0.75
     peat
    0.72
     miracle
    0.71
    你也
    0.70
    ถ้า
    0.70
    又
    0.69
     bargain
    0.68
     stabbing
    0.68
    POSITIVE LOGITS
     danych
    0.82
    数据的
    0.80
     inteligentes
    0.80
    американ
    0.75
     специали
    0.74
     متخصص
    0.74
     الکتر
    0.73
    wireless
    0.73
     Reboot
    0.73
    Formats
    0.72
    Activations Density 0.000%

    No Known Activations