© 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. 7514
    Prev
    Next
    INDEX
    Explanations

    avoiding casual phrasing and colloquialisms

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

    The neuron fires strongly on the very first substantive word of each new paragraph or section.

    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
    ↵↵
    0.82
    w
    0.75
    нка
    0.74
    Left
    0.72
    v
    0.72
    или
    0.71
    "
    0.71
    2
    0.71
    нки
    0.70
    {
    0.70
    POSITIVE LOGITS
     bioquímica
    0.96
     fibrosis
    0.92
     keselamatan
    0.90
     கல்லறை
    0.89
     construed
    0.86
    asign
    0.86
     💞
    0.85
     creatine
    0.84
     saúde
    0.83
     construye
    0.82
    Activations Density 0.000%

    No Known Activations