© 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. 24-GEMMASCOPE-2-RES-16K
    7. 7462
    Prev
    Next
    INDEX
    Explanations

    cloud provider resources

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

    The neuron primarily activates on the word “such,” especially when it appears in the phrase “such as.”

    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
    скільки
    0.77
    ycznych
    0.75
    ধানা
    0.74
     Гру
    0.67
    朱
    0.66
    øm
    0.64
     半
    0.64
     Enf
    0.64
     Đường
    0.63
     Stepan
    0.63
    POSITIVE LOGITS
     boomerang
    0.69
    emitter
    0.68
     hassle
    0.67
     dicta
    0.67
    getTo
    0.66
    buenas
    0.65
    ,
    0.65
     bekom
    0.64
    :
    0.63
    mutable
    0.63
    Activations Density 0.001%

    No Known Activations