© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15211
    Prev
    Next
    INDEX
    Explanations

    upper body

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

    The neuron fires strongly on phrases stating someone’s employment status or workplace (e.g. “working in …,” “currently stationed in …,” “in Defence sector,” etc.).

    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
     Siege
    0.68
    鰯
    0.67
     DispatchQueue
    0.63
     Spinach
    0.62
    stargo
    0.62
    vođa
    0.62
    鲇
    0.61
    efeu
    0.61
     Chọn
    0.61
     wichtigsten
    0.60
    POSITIVE LOGITS
    <strong>
    0.57
     teachers
    0.57
     above
    0.57
     department
    0.53
     child
    0.51
     teacher
    0.51
     Cip
    0.50
    <b>
    0.49
     now
    0.49
     company
    0.49
    Activations Density 0.215%

    No Known Activations