© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13558
    Prev
    Next
    INDEX
    Explanations

    difficult situations and topics

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

    The neuron responds to words that signal something is hard or complicated—mentions of difficulty or complexity.

    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
    残酷
    0.64
    olid
    0.62
    رات
    0.61
    ν
    0.60
    wght
    0.58
     fatigue
    0.57
    恐怖
    0.57
    errors
    0.56
    amon
    0.56
    ማ
    0.56
    POSITIVE LOGITS
     dific
    1.05
     difíciles
    1.02
     khăn
    0.95
    Difficult
    0.90
     Difficult
    0.89
    difficult
    0.89
     difícil
    0.88
     difficiles
    0.88
     difíc
    0.86
     schwier
    0.86
    Activations Density 0.162%

    No Known Activations