© 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. 9495
    Prev
    Next
    INDEX
    Explanations

    fun activities and engagement

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

    The neuron strongly fires on words expressing enjoyment or amusement (e.g. “fun,” “crazy”), i.e. mentions of having fun.

    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
    이면
    0.99
     reste
    0.89
     IUser
    0.89
     못한
    0.88
    І
    0.87
    уда
    0.86
     sadly
    0.86
     спокойно
    0.86
     শুনে
    0.86
     solace
    0.83
    POSITIVE LOGITS
    ا
    1.21
    nier
    1.13
    いろいろ
    1.05
     antics
    0.95
    tains
    0.95
    nies
    0.91
    nels
    0.86
    Fun
    0.84
    Основные
    0.84
     fun
    0.83
    Activations Density 0.029%

    No Known Activations