© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1129
    Prev
    Next
    INDEX
    Explanations

    list numbers and separators

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

    The neuron broadly activates on proper nouns—especially brand and place names.

    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
    ಚಿತ
    0.51
    níka
    0.48
    Результа
    0.44
     unwavering
    0.43
    следование
    0.42
    定的
    0.41
     eredmény
    0.41
    :...
    0.41
    ahuje
    0.41
    높
    0.41
    POSITIVE LOGITS
     etc
    0.46
     estan
    0.45
     ಹಾಗೂ
    0.43
     populares
    0.43
    などの
    0.43
    etc
    0.42
     classica
    0.42
     falam
    0.42
     Etc
    0.42
     इनमें
    0.42
    Activations Density 0.001%

    No Known Activations