© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8532
    Prev
    Next
    INDEX
    Explanations

    former colleagues, former employment

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

    This neuron fires on numeric tokens conveying counts or metric statistics (e.g. job counts, profile views).

    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_31_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
     camphor
    0.59
     iodine
    0.57
     chromospheric
    0.56
     marshes
    0.56
     sinks
    0.55
     rơi
    0.55
     reikia
    0.54
    像
    0.53
    oki
    0.53
     indig
    0.53
    POSITIVE LOGITS
     linkedin
    0.94
    linkedin
    0.90
     Linkedin
    0.87
    Linkedin
    0.83
     Demonstrated
    0.83
     LinkedIn
    0.81
    LinkedIn
    0.81
    EMPLOY
    0.75
    职务
    0.75
    Entrepreneur
    0.75
    Activations Density 0.109%

    No Known Activations