© 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. 9746
    Prev
    Next
    INDEX
    Explanations

    stress management

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

    The neuron detects professional résumé–style “Skilled in …” phrases that list someone’s expertise or abilities.

    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
    f
    1.09
    迋
    0.79
    s
    0.78
    ants
    0.77
    িতে
    0.76
    aldi
    0.76
     छुट्ट
    0.73
    ich
    0.73
    ’
    0.72
    ad
    0.70
    POSITIVE LOGITS
     amelyet
    0.86
    的环境
    0.79
    TabLayout
    0.77
     พื้น
    0.76
    infodisc
    0.75
    一开始
    0.75
    궂
    0.74
     موارد
    0.74
     بتوان
    0.73
    MathMarks
    0.73
    Activations Density 0.001%

    No Known Activations