© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4735
    Prev
    Next
    INDEX
    Explanations

    demographic and descriptive headings

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

    This neuron detects long all-caps letter sequences (e.g. uppercase words).

    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
    /
    0.83
    !(
    0.72
     &
    0.70
     YOUR
    0.70
    :
    0.67
    你的
    0.64
    &
    0.64
    _
    0.63
    :
    0.58
    :(
    0.57
    POSITIVE LOGITS
    に対し
    0.55
     immunohist
    0.54
     aortic
    0.51
     mononuclear
    0.49
    তাহাকে
    0.49
     juris
    0.48
     much
    0.48
    这样一个
    0.48
    দেখিতে
    0.47
    ,$
    0.47
    Activations Density 0.000%

    No Known Activations