© 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. 13390
    Prev
    Next
    INDEX
    Explanations

    nucleus formation or increment

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

    The neuron activates on words referring to waste‐disposal containers (e.g. “dumpster,” “excess” in the garbage context).

    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
     Мы
    0.80
     Ciencias
    0.76
    댈
    0.76
     Использу
    0.73
    ﺌ
    0.73
     Конечно
    0.72
     hablando
    0.69
     Можно
    0.69
     Тогда
    0.68
     podremos
    0.68
    POSITIVE LOGITS
     appréci
    0.73
     ascendent
    0.67
     mai
    0.65
    ikova
    0.65
    mi
    0.64
    chron
    0.63
    澈
    0.63
    cro
    0.61
     améli
    0.61
    sv
    0.60
    Activations Density 0.001%

    No Known Activations